Rust Path Types
openinterpreter/openinterpreter
Rules for choosing Rust types for filesystem paths in new Codex code, covering protocol types, internal use and model tool arguments.
Operate SendFox campaigns and audiences with typed commands, local evidence and guarded plans.
$ npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-sendfox --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-sendfox .claude/skills/pp-sendfox && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pp-sendfox" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfox into .claude/skills/pp-sendfox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-sendfox", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfoxType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-sendfox --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cli-skills/pp-sendfox .agents/skills/pp-sendfox && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pp-sendfox" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfox into .agents/skills/pp-sendfox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-sendfox", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-sendfox --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cli-skills/pp-sendfox .cursor/skills/pp-sendfox && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pp-sendfox" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfox into .cursor/skills/pp-sendfox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-sendfox", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mvanhorn/printing-press-library.git --path cli-skills/pp-sendfox--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-sendfox --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cli-skills/pp-sendfox .gemini/skills/pp-sendfox && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pp-sendfox" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfox into .gemini/skills/pp-sendfox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-sendfox", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mvanhorn/printing-press-library pp-sendfoxInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .github/skills && cp -r skills-src/cli-skills/pp-sendfox .github/skills/pp-sendfox && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pp-sendfox" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfox into .github/skills/pp-sendfox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-sendfox", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mvanhorn/printing-press-library pp-sendfox --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cli-skills/pp-sendfox .opencode/skills/pp-sendfox && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pp-sendfox" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-sendfox into .opencode/skills/pp-sendfox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-sendfox", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pp-sendfoxOperate SendFox campaigns and audiences with typed commands, local evidence and guarded plans.
Pp Sendfox is an agent skill from mvanhorn/printing-press-library. Operate SendFox campaigns and audiences with typed commands, local evidence and guarded plans. Trigger phrases: preflight a SendFox campaign, audit SendFox audience, plan an inactive SendFox automation, use sendfox, run sendfox.
Its SKILL.md is about 9.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 0fdcc7a. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
goclaudenpxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SENDFOX_API_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Sendfox loads about 9.5k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 3,940 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mvanhorn/printing-press-library at commit 0fdcc7a, republished under its Apache-2.0 licence (© mvanhorn). 3,940 words, ~9,512 tokens.
.claude/skills/pp-sendfox/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/marketing/sendfox/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
This edition covers the documented 60-operation SendFox contract. Discover current commands with which and capabilities. Preview every write with --dry-run; execution requires --yes, and sends, schedules, activation, forms/domains or deletion additionally require --approve-sensitive. Do not interpret an evidence report's ready value or exit 0 as permission to act. The eight evidence reports read local JSON/YAML/SQLite only; reject live data-source requests and report missing/stale scopes explicitly. workflow export-bundle is strictly read-only; workflow snapshot-save --out DIR is the explicit local-file write. See EVIDENCE.md for the normalized snapshot schema and native-export limitations. Read-only authenticated behavior passed the publish-time live gate; account mutations, sends and delivery remain unverified.
For bulk jobs, --preview-count controls the API's count-only request while global --dry-run stays entirely local. No writes are automatically retried. The account budget is 60 requests/minute shared with every other client. Use contacts bulk-wait with a bounded request count to inspect progress.
MCP search/metadata/execute tools cover 60 operations with schemas; mutations preview unless confirm=true, with approve_sensitive=true additionally required for high-impact actions. Endpoint mirrors are hidden. Local workflows remain explicit tools.
This skill drives the sendfox-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install sendfox --cli-onlysendfox-pp-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:
go install github.com/mvanhorn/printing-press-library/library/marketing/sendfox/cmd/sendfox-pp-cli@latestIf --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.
Manage the current SendFox API from a predictable CLI and compact MCP surface. Combine campaign, audience and automation evidence locally; evaluate migration readiness without changing an account.
Use this CLI for SendFox audience operations, campaign preparation and reports, automation definitions and deterministic local export comparisons. Inspect plans and completeness before acting.
Do not use this CLI for:
These workflows combine supplied local evidence into auditable reports and inactive plans.
workflow audience-health — Find duplicate, invalid, suppressed and unassigned contacts, plus honest engagement cohorts.
Engagement timestamps form recency cohorts; missing or incomplete activity stays unknown rather than being labeled never-engaged.
sendfox-pp-cli workflow audience-health --input examples/snapshot.json --agentworkflow campaign-preflight — Check draft content, targeting, suppression evidence and sender readiness before any send.
Check draft content, targeting, suppression evidence and sender readiness before any send.
sendfox-pp-cli workflow campaign-preflight --input examples/snapshot.json --agentworkflow campaign-review — Combine campaign metrics, recipient-weighted benchmarks, trends, link performance and engagement cohorts into an auditable resend plan.
Rates are recomputed from counters, recipient-weighted, and compared with campaign medians and timestamped trends.
sendfox-pp-cli workflow campaign-review --input examples/snapshot.json --agentworkflow contact-dossier — Join contact details, memberships, tags and available engagement into one support packet.
Join contact details, memberships, tags and available engagement into one support packet.
sendfox-pp-cli workflow contact-dossier --input examples/snapshot.json --id 1 --agentworkflow automation-plan — Validate a versioned automation definition and produce inactive creation steps.
Validate a versioned automation definition and produce inactive creation steps.
sendfox-pp-cli workflow automation-plan --input examples/snapshot.json --agentworkflow export-bundle — Produce a read-only local inventory bundle with completeness, provenance and deterministic hashes.
This command never writes files; use snapshot-save when durable history is intended.
sendfox-pp-cli workflow export-bundle --input examples/snapshot.json --agentworkflow growth-report — Calculate timestamped audience growth from one snapshot and exact observed list joins, leaves and retention from two.
Every metric includes its formula, window, numerator, denominator, evidence grade, completeness and warnings. Missing evidence is null, never an invented zero.
sendfox-pp-cli workflow growth-report --input current.json --previous previous.json --window 30d --agentworkflow migration-readiness — Compare local platform snapshots with suppression, mapping, delta and cutover gates.
Compare local platform snapshots with suppression, mapping, delta and cutover gates.
sendfox-pp-cli workflow migration-readiness --input examples/snapshot.json --agentworkflow snapshot-save is the explicit local-write companion to export-bundle. It requires --out, writes atomically with a 0700 directory and 0600 JSON file, and returns the artifact SHA-256.
sendfox-pp-cli workflow snapshot-save --input examples/snapshot.json --out ./history --agentautomation_emails — Manage automation emails
sendfox-pp-cli automation-emails delete — Remove an email from an automationsendfox-pp-cli automation-emails update — Update an automation emailautomations — Manage automations
sendfox-pp-cli automations create — Create an automationsendfox-pp-cli automations create-email — Add an email to an automationsendfox-pp-cli automations delete — Soft-deletes the automation and cancels all scheduled deliverablessendfox-pp-cli automations get — Returns automation with triggers, items, and campaign statssendfox-pp-cli automations list — List automationssendfox-pp-cli automations update — Update title, trigger, or active status. Activating reschedules stale deliverables.campaigns — Manage campaigns
sendfox-pp-cli campaigns create — Creates a campaign as a draft. To send it, use the send endpoint or provide scheduled_at.sendfox-pp-cli campaigns delete — Only draft campaigns (not yet sent) can be deleted. Uses soft delete.sendfox-pp-cli campaigns get — Get a specific campaignsendfox-pp-cli campaigns get-stats — Returns sent count and open/click/bounce/unsubscribe/spam counts and rates, all read from stored counters.sendfox-pp-cli campaigns list — Returns a paginated list of campaigns (100 per page)sendfox-pp-cli campaigns list-engagement — Returns the contacts in one of a sent campaign's engagement groups.sendfox-pp-cli campaigns resend — Creates a new draft with the original's content, sender, and exclusionssendfox-pp-cli campaigns send — Schedules a draft campaign for immediate sending.sendfox-pp-cli campaigns update — Only draft campaigns (not yet sent) can be updated. All fields are optional.contact_fields — Manage contact fields
sendfox-pp-cli contact-fields create — Creates a custom field for contacts. The name is auto-generated from the label as a slug.sendfox-pp-cli contact-fields delete — Permanently deletes the contact fieldsendfox-pp-cli contact-fields get — Get a specific contact fieldsendfox-pp-cli contact-fields list — Returns custom contact fields defined by the user (20 per page)sendfox-pp-cli contact-fields update — Updates the label and auto-regenerates the name slug.contact_tags — Manage contact tags
sendfox-pp-cli contact-tags create — Creates a tag. A brand color is auto-assigned when none is provided. Tag names are unique per account.sendfox-pp-cli contact-tags delete — Deletes the tag.sendfox-pp-cli contact-tags get — Get a contact tagsendfox-pp-cli contact-tags list — Lists the account's tags, newest first, each with its contact count.sendfox-pp-cli contact-tags update — Update a contact tagcontacts — Manage contacts
sendfox-pp-cli contacts attach-tag — Idempotent. Returns the contact's tags after the change.sendfox-pp-cli contacts batch-import — Import up to 1,000 contacts in a single request. Creates new contacts or updates existing ones.sendfox-pp-cli contacts create — Create a new contactsendfox-pp-cli contacts create-bulk-action — Queues one action against every contact the filter matches, applied in chunks in the background.sendfox-pp-cli contacts delete — Soft-deletes a contact and cancels any scheduled deliverablessendfox-pp-cli contacts detach-tag — Remove a tag from a contactsendfox-pp-cli contacts get — Get a specific contactsendfox-pp-cli contacts get-activity — Returns paginated email deliverables and contact-level engagement summarysendfox-pp-cli contacts get-bulk-action — For a dry run, matched_count is the answer and nothing was modified.sendfox-pp-cli contacts list — Returns a paginated list of contacts (100 per page by default, up to 1000 via per_page).sendfox-pp-cli contacts list-tags-for — List a contact's tagssendfox-pp-cli contacts list-unsubscribed — List unsubscribed contactssendfox-pp-cli contacts update — Update contact details including name, list memberships, and custom fieldsdomains — Manage domains
sendfox-pp-cli domains create — Adds a new sender domain and creates the corresponding SendGrid whitelabel domain.sendfox-pp-cli domains delete — Removes the domain from SendGrid and soft-deletes locallysendfox-pp-cli domains get — Returns domain details including DNS records needed for verificationsendfox-pp-cli domains list — Returns a paginated list of the user's whitelabel/sender domainssendfox-pp-cli domains validate — Triggers DNS validation for the domain via SendGrid.forms — Manage forms
sendfox-pp-cli forms create — Creates a subscription form linked to one or more lists. Free users are limited to 1 form.sendfox-pp-cli forms delete — Soft-deletes the formsendfox-pp-cli forms get — Get a specific formsendfox-pp-cli forms list — List formssendfox-pp-cli forms update — Update a formlists — Manage lists
sendfox-pp-cli lists add-contact-to — Adds an existing contact to a list. If the contact is already in the list, no duplicate is created.sendfox-pp-cli lists contacts-in — Get contacts in a listsendfox-pp-cli lists create — Create a new contact listsendfox-pp-cli lists delete — Soft-deletes a list. Returns 409 if the list is used by forms, landing pages, or automations.sendfox-pp-cli lists get — Returns list details including average open and click ratessendfox-pp-cli lists list-lists — List contact listssendfox-pp-cli lists remove-contact-from — Remove a contact from a listsendfox-pp-cli lists update — Update a contact listme — Manage me
sendfox-pp-cli me — Get current user informationunsubscribe — Manage unsubscribe
sendfox-pp-cli unsubscribe — Unsubscribe a contact by emailWhen you know what you want to do but not which command does it, ask the CLI directly:
sendfox-pp-cli which "campaign statistics"which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.
sendfox-pp-cli workflow audience-health --input examples/snapshot.json --agentReport hygiene issues using local snapshot evidence.
sendfox-pp-cli workflow export-bundle --input examples/snapshot.json --agent --select data.countsSelect only resource counts from the evidence bundle.
sendfox-pp-cli workflow migration-readiness --input examples/snapshot.json --agentProduce a fail-closed readiness report; missing Kit evidence remains unknown.
sendfox-pp-cli workflow campaign-preflight --input examples/snapshot.json --agentCheck content, targeting and sender evidence without sending.
sendfox-pp-cli workflow campaign-review --input examples/snapshot.json --agentRead counters and links and produce an unscheduled resend plan.
sendfox-pp-cli workflow contact-dossier --input examples/snapshot.json --id 1 --agentJoin the selected synthetic contact with memberships and activity.
sendfox-pp-cli workflow automation-plan --input examples/snapshot.json --agentCompile dependent creation requests with active=false.
sendfox-pp-cli contacts audit-csv --file examples/contacts.csv --agentInspect malformed, duplicate and suppressed rows before any import.
sendfox-pp-cli campaigns create --title "September notes" --subject "September notes" --from-email "editor@example.com" --from-name "Example Editor" --html "<p>News</p>" --dry-run --agentValidate and preview a draft request; no account request is made.
Run sendfox-pp-cli auth setup for the URL and steps to obtain a token (add --launch to open the URL):
Or set SENDFOX_API_TOKEN as an environment variable.
Run sendfox-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color.
Global format flags share one contract on promoted, novel, sync, and --deliver paths:
--json — one JSON document on stdout (sync progress events go to stderr)
--compact — keep identity/status/timestamp fields; does not change the document vs stream shape
--csv / --plain — tabular rows (collection envelopes unwrap to the row array)
--quiet — one identity value per row, no envelope
Pipeable — JSON on stdout, errors on stderr
Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
sendfox-pp-cli automations list --agent --select active,automation_items,automation_triggersPreviewable — --dry-run shows the request without sending
Offline-friendly — sync/search commands can use the local SQLite store when available
Non-interactive — never prompts, every input is a flag
Explicit confirmation — --agent does not imply --yes; pass --yes separately only after the target, arguments, and side effects are clear
Explicit retries — use --idempotent only when an already-existing create should count as success, and use --ignore-missing only when a missing delete target should count as success
Commands that read from the local store or the API wrap output in a provenance envelope:
{
"meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
"results": <data>
}Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.
Agents should treat the CLI's path resolver as part of the runtime contract:
Use --home <dir> for one invocation, or set SENDFOX_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: SENDFOX_CONFIG_DIR, SENDFOX_DATA_DIR, SENDFOX_STATE_DIR, SENDFOX_CACHE_DIR.
Resolution order is per-kind env var, --home, SENDFOX_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.
config contains settings like config.toml and profiles. data contains credentials.toml, credential-scoped data-<hash>.db files, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.
Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.
Authenticated default stores are isolated by a one-way credential hash. Never treat an unscoped legacy data.db as belonging to the active account; run sync to populate the scoped store. An explicit --db is an operator-controlled override.
Run sendfox-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.
For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:
{
"mcpServers": {
"sendfox": {
"command": "sendfox-pp-mcp",
"env": {
"SENDFOX_HOME": "/srv/sendfox"
}
}
}
}Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use SENDFOX_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing SENDFOX_HOME, or doctor will not find credentials left under the former root.
This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.
recall before any discoveryBefore list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.
Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:
# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
sendfox-pp-cli recall "$QUERY" --agentPrefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.
The response envelope:
{
"query": "...",
"normalized": "<normalized form>",
"query_entities": ["..."],
"found": true | false,
"match_score": 0.0,
"results": [
{ "resource_id": "...", "resource_type": "...", "venue": "...",
"confidence": 2, "entity_match": "exact|partial|unknown",
"source": "taught|preseed|pattern", "warnings": ["..."] }
],
"mismatches": [ /* only when --debug-mismatches */ ],
"warnings": [ /* top-level */ ],
"candidates": [
{ "id": 12, "class": "flag_alias | playbook_candidate",
"summary": "...", "sightings": 3, "last_seen": "...",
"rationale": "...",
"next_action": ["<trial command>", "sendfox-pp-cli learnings confirm 12"] }
],
"playbook": {
"query_family": "...",
"playbook": {
"steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
"entity_slots": ["$ENTITY"],
"expected_tool_calls": 3
},
"slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
"notes": "<workarounds + gotchas for this query family>"
},
"notes": "<duplicate surface for non-playbook callers>"
}Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.
Read candidates, playbook, notes, results[0], and warnings in that order:
if Candidates present (warnings include "candidates_present"):
-> candidates are try-then-confirm, never facts. Follow each candidate's
two-step next_action verbatim: run the trial command first, then run
`learnings confirm <id>` only after the trial verified the behavior.
Reject a wrong candidate with `learnings reject <id>`.
-> NEVER re-teach something recall surfaced as a candidate; confirm or
reject that candidate instead of teaching a duplicate.
-> candidates ride alongside playbooks and resource hits, not instead of
them; continue with the branches below after acting on them.
if Playbook present:
-> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
-> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
for the entity slot tokens. If a step's slot is unresolved, fall back to
discovery for that step only.
-> the Playbook's expected_tool_calls is a budget; if you find yourself running
materially more, record the divergence via `sendfox-pp-cli playbook amend`
at end-of-session.
elif Notes present (no Playbook):
-> read Notes verbatim before any discovery step; they carry known gotchas
for this query family even when no structured choreography exists yet.
elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
-> skip discovery; fetch live data for Results[*].ResourceID in parallel
elif Found AND Results[0].EntityMatch == "partial":
-> candidate hint, NOT a hit; read the resource title to validate before trusting
elif (any row in Mismatches[] when --debug-mismatches was passed):
-> treat as cold start; the stored learning is for a different entity
(different canonical resolved from query_entities)
else: // Found == false, no playbook, no notes
-> cold start; run discovery normally; teach the answer afterward (Step 4).
If the family has no playbook yet, that teach auto-synthesizes a
playbook candidate from this session's journal - you do not need to
record one by hand.Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.
Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; sendfox-pp-cli learnings candidates lists the full open set.
Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.
warningslow_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run sendfox-pp-cli sync to refresh entity lookups.no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.teach & after finalizing your response - alwaysTeaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell & so the call returns immediately. Pass the query the same way as recall — argv/MCP, or file-then-$QUERY. Do not splice the question into the command text:
QUERY=$(cat /path/to/question.txt)
sendfox-pp-cli teach --query "$QUERY" --resource-type campaigns --resource 42
# (append shell `&` to background it)Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.
PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.
You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:
# Common case: record both the resource learning AND the playbook in one call.
QUERY=$(cat /path/to/question.txt)
sendfox-pp-cli teach \
--query "$QUERY" \
--resource 42 \
--playbook-file ./playbooks/campaign-review.json \
--playbook-notes-file ./playbooks/campaign-review-notes.md
# (append shell `&` to background it)
# Alternate: playbook-only (no resource to record alongside).
QUERY=$(cat /path/to/question.txt)
sendfox-pp-cli teach-playbook \
--query "$QUERY" \
--playbook-file ./playbooks/campaign-review.json \
--notes-file ./playbooks/campaign-review-notes.mdPlaybook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.
When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.
playbook amend & when your debug response identifies a correctionIf your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (QUERY=$(cat ...), NOTE=$(cat ...)). Do not interpolate either string into the command text:
QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
sendfox-pp-cli playbook amend \
--query "$QUERY" \
--add-note "$NOTE"
# (append shell `&` to background it)What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending:
{meta, results}, payload nested two levels deeper than the docs claim).What does NOT belong in notes:
The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land).
playbook amend notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing:
If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.
sendfox-pp-cli learnings stats reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local learn_events table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI.
--no-learn on a single command short-circuits both recall and the teach write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings.SENDFOX_NO_LEARN=true in the environment globally disables the pipeline.When you (or the agent) notice something off about this CLI, record it:
sendfox-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
sendfox-pp-cli feedback --stdin < notes.txt
sendfox-pp-cli feedback list --json --limit 10Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless SENDFOX_FEEDBACK_ENDPOINT is set AND either --send is passed or SENDFOX_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect |
|---|---|
stdout | Default; write to stdout only |
file:<path> | Atomically write output to <path> (tmp + rename). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; --json/--csv do not refuse when this sink is set. |
webhook:<url> | POST the output body to the URL (application/json) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run.
sendfox-pp-cli profile save briefing --json
sendfox-pp-cli --profile briefing automations list
sendfox-pp-cli profile list --json
sendfox-pp-cli profile show briefing
sendfox-pp-cli profile delete briefing --yesExplicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Usage error (wrong arguments) |
| 3 | Resource not found |
| 4 | Authentication required |
| 5 | API error (upstream issue) |
| 6 | Partial failure |
| 7 | Rate limited (wait and retry) |
| 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show sendfox-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)go install github.com/mvanhorn/printing-press-library/library/marketing/sendfox/cmd/sendfox-pp-mcp@latestclaude mcp add sendfox-pp-mcp -- sendfox-pp-mcpclaude mcp listwhich sendfox-pp-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:sendfox-pp-cli capabilities --agentsendfox-pp-cli campaigns --help.© mvanhorn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in cli-skills/pp-sendfox of mvanhorn/printing-press-library.
Open the folder on GitHubat commit 0fdcc7a
Pp Sendfox next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pp Sendfox this skillmvanhorn/printing-press-library | 2.1k | — | ~9.5k | Automated safety check: Notes | Apache-2.0 | |
| Rust Path Typesopeninterpreter/openinterpreter | 69k | 2 repos | ~605 | Automated safety check: Pass | Apache-2.0 | |
| Python Type Safetywshobson/agents | 40k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Campaign Operations Knowledge Builderlimecloud/lime | 1.5k | — | ~715 | Automated safety check: Pass | Apache-2.0 | |
| Pyrefly Type Coveragepytorch/pytorch | 104k | — | ~3k | Automated safety check: Pass | Custom licence | |
| Marketing Campaignaffaan-m/ECC | 275k | 1 repos | ~1.3k | Automated safety check: Pass | MIT |
openinterpreter/openinterpreter
Rules for choosing Rust types for filesystem paths in new Codex code, covering protocol types, internal use and model tool arguments.
wshobson/agents
Python type safety with type hints, generics, protocols, and strict type checking.
limecloud/lime
将活动目标、用户路径、渠道分工、物料资产、时间节奏、风险预案和复盘结论等资料,整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理活动 / Campaign 运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。
pytorch/pytorch
Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.
affaan-m/ECC
End-to-end marketing campaign planning and execution. An agent skill from affaan-m/ECC.
davila7/claude-code-templates
Manages IT infrastructure, monitoring, incident response, and service reliability.
mvanhorn/printing-press-library
Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.
mvanhorn/printing-press-library
Search, browse, and download Google Fonts from the terminal via the gfonts CLI.
mvanhorn/printing-press-library
The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.
mvanhorn/printing-press-library
Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.
mvanhorn/printing-press-library
Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...
mvanhorn/printing-press-library
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.
Operate SendFox campaigns and audiences with typed commands, local evidence and guarded plans. Pp Sendfox is an agent skill from mvanhorn/printing-press-library. Operate SendFox campaigns and audiences with typed commands, local evidence and guarded plans.
Pp Sendfox fits situations like: phrases: preflight a SendFox campaign; audit SendFox audience; plan an inactive SendFox automation.
Run `npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a claude-code`. Or copy the skill folder (cli-skills/pp-sendfox in mvanhorn/printing-press-library) into .claude/skills/pp-sendfox in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a codex`. Or copy the skill folder (cli-skills/pp-sendfox in mvanhorn/printing-press-library) into .agents/skills/pp-sendfox in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-sendfox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-sendfox, .gemini/skills/pp-sendfox, .github/skills/pp-sendfox and .opencode/skills/pp-sendfox in your project.
Going by SKILL.md and its folder, Pp Sendfox needs the command-line tools its instructions call (go, claude and npx) and credentials named SENDFOX_API_TOKEN. Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Pp Sendfox is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 9.5k tokens (SKILL.md is roughly 38k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Pp Sendfox: Rust Path Types (openinterpreter/openinterpreter, 69k stars), Python Type Safety (wshobson/agents, 40k stars), Campaign Operations Knowledge Builder (limecloud/lime, 1.5k stars) and Pyrefly Type Coverage (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,053 GitHub stars. The repository holds 505 skills in this directory. The repository was last updated on October 7, 2026.
Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.