Sites
asgeirtj/system_prompts_leaks
A skill your agent uses when creating or updating a website, web app, or browser game, or when a visual layout or interactive tool would help with what the user is doing.
Search Immovlan from the terminal with every site filter, keep a local history, and cross it with Immoweb: exclusives, re-listings, rented PEB F/G traps and division candidates.
$ npx skills add mvanhorn/printing-press-library --skill pp-immovlan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-immovlan --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-immovlan .claude/skills/pp-immovlan && 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-immovlan" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-immovlan into .claude/skills/pp-immovlan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-immovlan", 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-immovlanType 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-immovlan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-immovlan --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-immovlan .agents/skills/pp-immovlan && 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-immovlan" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-immovlan into .agents/skills/pp-immovlan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-immovlan", 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-immovlan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-immovlan --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-immovlan .cursor/skills/pp-immovlan && 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-immovlan" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-immovlan into .cursor/skills/pp-immovlan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-immovlan", 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-immovlan--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-immovlan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-immovlan --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-immovlan .gemini/skills/pp-immovlan && 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-immovlan" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-immovlan into .gemini/skills/pp-immovlan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-immovlan", 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-immovlanInstalls 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-immovlan -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-immovlan .github/skills/pp-immovlan && 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-immovlan" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-immovlan into .github/skills/pp-immovlan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-immovlan", 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-immovlan -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-immovlan --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-immovlan .opencode/skills/pp-immovlan && 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-immovlan" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-immovlan into .opencode/skills/pp-immovlan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-immovlan", 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-immovlanSearch Immovlan from the terminal with every site filter, keep a local history, and cross it with Immoweb: exclusives, re-listings, rented PEB F/G traps and division candidates.
Pp Immovlan is an agent skill from mvanhorn/printing-press-library. Search Immovlan from the terminal with every site filter, keep a local history, and cross it with Immoweb: exclusives, re-listings, rented PEB F/G traps and division candidates. Trigger phrases: search immovlan, what is for sale on immovlan in schaerbeek, PEB F houses on immovlan, is this immovlan listing also on immoweb, immovlan exclusives, use immovlan, run immovlan.
Its SKILL.md is about 7.8k 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 76de244. 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Immovlan loads about 7.8k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 3,311 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 76de244, republished under its Apache-2.0 licence (© mvanhorn). 3,311 words, ~7,848 tokens.
.claude/skills/pp-immovlan/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/other/immovlan/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 skill drives the immovlan-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install immovlan --cli-onlyimmovlan-pp-cli --version$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/other/immovlan/cmd/immovlan-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.
Reads the same server-rendered pages the immovlan.be site serves, with no login, and stores every result in SQLite. Field names mirror immoweb-pp-cli so a sourcing job can merge both portals, and same-as tells you which listings exist only on Immovlan. enrich fills the detail fields the search cards never show, and peb-trap, split-candidates and relisted answer the questions a property trader asks before calling an agency.
Reach for this CLI when a task needs Belgian listings from Immovlan: searching a commune with price, bedroom and PEB filters, reading a listing's full details, tracking what is new or cheaper, or crossing Immovlan with Immoweb for a property trader's sourcing. It is the second portal next to immoweb-pp-cli in the brussels-peb-hunter job.
Do not use this CLI for:
These capabilities aren't available in any other tool for this API.
same-as — Tell whether a stored Immovlan listing is also on Immoweb, at what price, or is Immovlan-only.
Use it to dedupe a cross-portal sourcing run or to find Immovlan exclusives before calling an agency. Requires immoweb-pp-cli's local store (--immoweb-db or $IMMOWEB_PP_DB); run enrich --missing street first so addresses can match. Every row carries flat immoweb_id (0 when Immovlan-only), immoweb_url, immoweb_price, delta_pct, match_status (address / surface_bedrooms_agency / none) and immoweb_gone_status; the nested immoweb object exists on matched rows only and is dropped by --agent compaction, so agents read the flat fields.
immovlan-pp-cli same-as --all --unmatched --postcode 1030 --agentagencies — Which agencies list in a zone, their PEB F/G share, private-seller share and the CRM software behind each feed.
Use it to see which feeds are syndicated (likely also on Immoweb) versus Rossel-exclusive. The software column stays ? until enrich has read the listing pages.
immovlan-pp-cli agencies --postcode 1030 --epc F,G --agentpeb-trap — List PEB F or G properties that are currently rented: owners who can no longer re-let in Brussels since 2026.
Use it when the question is which sellers are structurally motivated, not merely cheap. Needs enrich --missing epc,rented first; --include-unknown also lists F/G rows not yet enriched.
immovlan-pp-cli peb-trap --postcode 1030,1210 --max-price 2500000 --agentsplit-candidates — Houses large enough to divide, ranked by €/m² within their postcode, with land, year, PEB and rented flags.
Use it for a trader who divides houses into apartments; find cannot filter by surface.
immovlan-pp-cli split-candidates --min-surface 200 --postcode 1030 --agentenrich — Fill missing detail fields (PEB letter, street, geo, rented, cadastral income, agency software) for many stored listings in one resumable pass.
Run it after find and before peb-trap, same-as or split-candidates so their inputs exist.
immovlan-pp-cli enrich --missing epc,rented --top 150 --agentrelisted — Listings that came back under a new reference, with their true first-seen date and price at each reference.
Use it to expose a fake Nouveau before negotiating on ancienneté.
immovlan-pp-cli relisted --since 90d --postcode 1030 --agentlistings — Immovlan listings: server-rendered search pages (20 cards per page) and detail pages
immovlan-pp-cli listings get — Fetch one listing page by reference (e.g. vbe69761); Immovlan redirects to the canonical URL. Returns the schema.immovlan-pp-cli listings search — Search listings; returns the detail links of one result page (20 per page).Sourcing workflow (hand-written, all read the local store data.db after find)
immovlan-pp-cli find — Search by type, deal, postcode/commune, price band, PEB band and sort; stores every card locally. Cards carry no street: run enrich for addresses.immovlan-pp-cli show <ref> — One listing's detail (PEB letter, surface, price, publication date, rented, cadastral income, agency or private).immovlan-pp-cli photos <ref> --dir <dir> — Download a listing's photos (CLI only, not exposed over MCP; existing files are never overwritten). Over MCP, read pictures from show.immovlan-pp-cli saved add|list|remove — Named searches; watch <name> re-runs one and reports new, price-changed and gone listings since the previous run.immovlan-pp-cli drops — Price drops recorded across runs.immovlan-pp-cli hide <ref> / shortlist <ref> — Local triage flags applied to every listing table.immovlan-pp-cli dump --format csv|jsonl|geojson — Export the store; locations --query <commune> lists the postcodes behind a commune name.When you know what you want to do but not which command does it, ask the CLI directly:
immovlan-pp-cli which "rented PEB F houses"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.
immovlan-pp-cli find --type maison --deal sale --postcode 1030,1210 --epc F,G --pages 5 --agent --select id,url,price,surface_m2,price_per_m2,epc,localityOne line per listing with the fields the sourcing job needs; --select keeps the payload small.
immovlan-pp-cli enrich --missing epc,rented --top 200 --agent && immovlan-pp-cli peb-trap --postcode 1030 --agentenrich reads the detail pages once; peb-trap then filters locally.
immovlan-pp-cli same-as --all --unmatched --postcode 1030 --agentJoins with immoweb-pp-cli's store; unmatched rows are listings only Immovlan carries.
immovlan-pp-cli saved add sch-fg --type maison,appartement --deal sale --postcode 1030 && immovlan-pp-cli watch sch-fg --agentFirst run is a baseline; later runs report new, price-changed and gone listings since the previous run.
immovlan-pp-cli find --deal public-sale --postcode 1030,1080 --agentImmovlan's own public-sale feed, next to Biddit.
No authentication required.
Run immovlan-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, and --deliver paths:
--json — one JSON document on stdout (progress notes 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:
immovlan-pp-cli listings get vbe69761 --agent --select url,name,datePostedPreviewable — --dry-run shows the request without sending
One JSON shape — find, watch, drops, relisted, peb-trap, split-candidates, agencies and same-as return an object with results plus counters and an optional note (an empty store is a note, not an error); dump --agent returns the bare array. watch price changes carry old_price, new_price, change_pct.
Offline-friendly — find, watch and enrich store every page in SQLite; drops, peb-trap, split-candidates, relisted, agencies, same-as, dump and shortlist read it offline; show --data-source local prints the stored row
Non-interactive — never prompts, every input is a flag
Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests
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 IMMOVLAN_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: IMMOVLAN_CONFIG_DIR, IMMOVLAN_DATA_DIR, IMMOVLAN_STATE_DIR, IMMOVLAN_CACHE_DIR.
Resolution order is per-kind env var, --home, IMMOVLAN_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 data.db (the listing store); this CLI has no credentials, cookies or auth files. state contains teach.log and the learn journal. cache contains regenerable HTTP/cache files.
Run immovlan-pp-cli doctor --fail-on warn to surface path 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": {
"immovlan": {
"command": "immovlan-pp-mcp",
"env": {
"IMMOVLAN_HOME": "/srv/immovlan"
}
}
}
}Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use IMMOVLAN_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 IMMOVLAN_HOME, or doctor will not find the store 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)
immovlan-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>", "immovlan-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 `immovlan-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; immovlan-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.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)
immovlan-pp-cli teach --query "$QUERY" --resource-type <type> --resource <id1> --resource <id2>
# (append shell `&` to background it)Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.
PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.
You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:
# Common case: record both the resource learning AND the playbook in one call.
QUERY=$(cat /path/to/question.txt)
immovlan-pp-cli teach \
--query "$QUERY" \
--resource <id> \
--playbook-file ~/playbooks/<shape>.json \
--playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)
# Alternate: playbook-only (no resource to record alongside).
QUERY=$(cat /path/to/question.txt)
immovlan-pp-cli teach-playbook \
--query "$QUERY" \
--playbook-file ~/playbooks/<shape>.json \
--notes-file ~/playbooks/<shape>-notes.mdPlaybook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.
When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.
playbook amend & when your debug response identifies a correctionIf your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (QUERY=$(cat ...), NOTE=$(cat ...)). Do not interpolate either string into the command text:
QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
immovlan-pp-cli playbook amend \
--query "$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.
immovlan-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.IMMOVLAN_NO_LEARN=true in the environment globally disables the pipeline.When you (or the agent) notice something off about this CLI, record it:
immovlan-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
immovlan-pp-cli feedback --stdin < notes.txt
immovlan-pp-cli feedback list --json --limit 10Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless IMMOVLAN_FEEDBACK_ENDPOINT is set AND either --send is passed or IMMOVLAN_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.
immovlan-pp-cli profile save briefing --json
immovlan-pp-cli --profile briefing listings get vbe69761
immovlan-pp-cli profile list --json
immovlan-pp-cli profile show briefing
immovlan-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 | Blocked (HTTP 401/403 on the generic listings commands or doctor: bot wall, geography or rate block; no credentials exist) |
| 5 | API error (also a 403 or bot challenge met by find, show, watch, enrich) |
| 7 | Rate limited (wait and retry) |
| 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show immovlan-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)go install github.com/mvanhorn/printing-press-library/library/other/immovlan/cmd/immovlan-pp-mcp@latestclaude mcp add immovlan-pp-mcp -- immovlan-pp-mcpclaude mcp listwhich immovlan-pp-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:immovlan-pp-cli peb-trap --postcode 1030 --agentimmovlan-pp-cli find --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-immovlan of mvanhorn/printing-press-library.
Open the folder on GitHubat commit 76de244
Pp Immovlan 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 Immovlan this skillmvanhorn/printing-press-library | 2.1k | — | ~7.8k | Automated safety check: Notes | Apache-2.0 | |
| Sitesasgeirtj/system_prompts_leaks | 69k | — | ~1.6k | Automated safety check: Pass | CC0-1.0 | |
| Terminal Openeraffaan-m/ECC | 276k | — | ~635 | Automated safety check: Pass | MIT | |
| Filterzalando/skipper | 3.3k | — | ~527 | Automated safety check: Pass | MIT | |
| Terminal Opsaffaan-m/ECC | 276k | 2 repos | ~750 | Automated safety check: Pass | MIT | |
| Terminal Opsaffaan-m/ECC | 276k | — | ~439 | Automated safety check: Pass | MIT |
asgeirtj/system_prompts_leaks
A skill your agent uses when creating or updating a website, web app, or browser game, or when a visual layout or interactive tool would help with what the user is doing.
affaan-m/ECC
Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery…
zalando/skipper
Create or modify code in the filters package and all its sub-folders
affaan-m/ECC
Evidence-first repo execution workflow for ECC. An agent skill from affaan-m/ECC.
affaan-m/ECC
ECCのための証拠優先のリポジトリ実行ワークフロー。ユーザーがコマンドの実行、リポジトリの確認、CIの失敗のデバッグ、正確な実行と検証の証明を伴う狭い修正のプッシュを必要とする場合に使用する。
affaan-m/ECC
基于证据优先的仓库执行工作流,适用于ECC。当用户需要运行命令、检查仓库、调试CI失败或推送带有精确执行和验证证明的窄修复时使用。
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.
Search Immovlan from the terminal with every site filter, keep a local history, and cross it with Immoweb: exclusives, re-listings, rented PEB F/G traps and division candidates. Pp Immovlan is an agent skill from mvanhorn/printing-press-library. Search Immovlan from the terminal with every site filter, keep a local history, and cross it with Immoweb: exclusives, re-listings, rented PEB F/G traps and division candidates.
Pp Immovlan fits situations like: phrases: search immovlan; what is for sale on immovlan in schaerbeek; PEB F houses on immovlan; is this immovlan listing also on immoweb.
Run `npx skills add mvanhorn/printing-press-library --skill pp-immovlan -a claude-code`. Or copy the skill folder (cli-skills/pp-immovlan in mvanhorn/printing-press-library) into .claude/skills/pp-immovlan in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-immovlan -a codex`. Or copy the skill folder (cli-skills/pp-immovlan in mvanhorn/printing-press-library) into .agents/skills/pp-immovlan 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-immovlan -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-immovlan, .gemini/skills/pp-immovlan, .github/skills/pp-immovlan and .opencode/skills/pp-immovlan in your project.
Going by SKILL.md and its folder, Pp Immovlan needs the command-line tools its instructions call (go, claude and npx). 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 Immovlan 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 7.8k tokens (SKILL.md is roughly 31k 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 Immovlan: Sites (asgeirtj/system_prompts_leaks, 69k stars), Terminal Opener (affaan-m/ECC, 276k stars), Filter (zalando/skipper, 3.3k stars) and Terminal Ops (affaan-m/ECC, 276k 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 2,056 GitHub stars. The repository holds 506 skills in this directory. The repository was last updated on October 9, 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.