Pp Conductor

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/developer-tools/conductor/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/". -->

Conductor Cloud — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the conductor-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install conductor --cli-only

2. Verify: conductor-pp-cli --version
3. Ensure the reported install directory is on $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/developer-tools/conductor/cmd/conductor-pp-cli@latest

If --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.

Use launch, monitor, steer, and run to control coding-agent work without relying on the desktop app. The CLI treats status changes, transcript cursors, cancellation, and timeouts as one lifecycle instead of unrelated API calls.

When to Use This CLI

Use this CLI for Conductor Cloud project, workspace, session, message, and transcript operations. Prefer the workflow commands when a task spans several API calls or depends on asynchronous status. Do not use it to read Linear issues; ENG-526 owns that integration.

Anti-triggers

Do not use this CLI for:

• Reading or updating Linear issues
• Merging pull requests or deploying code
• Running local Conductor desktop-only workflows

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Bounded agent orchestration

• launch — Create a workspace and first session, send a brief, and return the Conductor deep link.

  Use this when an agent needs a new isolated Conductor workspace and task in one call.

  conductor-pp-cli launch --repository-url https://github.com/example/acme --branch main --harness codex --model gpt-5.4 --effort high --brief-file issue.md --agent

• run — Launch, monitor, and collect the final transcript and deep link with explicit timeout rules.

  Use this when the caller needs a complete Conductor task receipt, not just a launched workspace.

  conductor-pp-cli run --repository-url https://github.com/example/acme --branch main --harness codex --model gpt-5.4 --effort high --brief-file issue.md --timeout 30m --agent

• plan-implement — Keep a planner or reviewer session separate from the implementation session in one workspace.

  Use this when implementation should start from an explicit plan without mixing planner and coder context.

  conductor-pp-cli plan-implement --repository-url https://github.com/example/acme --branch main --planner-agent claude --implementer-agent codex --brief-file issue.md --agent

Safe lifecycle control

• monitor — Poll a session until real completion while streaming only new transcript events.

  Use this instead of treating one idle response as proof that a queued task finished.

  conductor-pp-cli monitor sess_123 --timeout 30m --interval 5s --dry-run --agent

• steer — Send follow-up guidance to an existing Conductor session with a clear delivery receipt.

  Use this to correct or refine active work without creating another session.

  conductor-pp-cli steer sess_123 --message 'Run the focused tests before changing the schema' --dry-run --agent

Transcript operations

• daily-report — Return recent Conductor session rows and mechanical activity totals from transcript search.

  Use this for a compact, deterministic activity feed that another agent can analyze.

  conductor-pp-cli daily-report --since 24h --limit 50 --agent

Command Reference

me — Manage me

• conductor-pp-cli me — Get authenticated identity.

messages — Manage messages

• conductor-pp-cli messages <messageId> — Get a message.

projects — Manage projects

• conductor-pp-cli projects get — Get a project.
• conductor-pp-cli projects list — List projects.

roundhouse-public-sql — Manage roundhouse public sql

• conductor-pp-cli roundhouse-public-sql — Runs a single read-only SQL SELECT statement over your organization's session transcripts and returns the matching rows.

sessions — Manage sessions

• conductor-pp-cli sessions create — Creates a session in an existing workspace.
• conductor-pp-cli sessions get — Get a session.

workspaces — Manage workspaces

• conductor-pp-cli workspaces create — Creates a cloud workspace and first session
• conductor-pp-cli workspaces get — Get a workspace.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

conductor-pp-cli which "<capability in your own words>"

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.

Recipes

Monitor an existing session

conductor-pp-cli monitor sess_123 --timeout 30m --interval 5s --agent

Streams incremental events and returns only after the task has demonstrably started and later completed.

Send steering guidance

conductor-pp-cli steer sess_123 --message 'Keep the change scoped to the parser' --agent

Adds guidance to the current session without creating a second workspace.

Review recent work

conductor-pp-cli daily-report --since 24h --limit 50 --agent

Returns mechanical session activity for downstream review or reporting.

Auth Setup

Set CONDUCTOR_API_KEY to a Conductor Cloud API key. The CLI sends it only as a bearer token to api.conductor.build and never prints it.

Run conductor-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• 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:

  conductor-pp-cli me --agent --select id,name,status

• Previewable — --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 retries — use --idempotent only when an already-existing create should count as success

Response envelope

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.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set CONDUCTOR_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: CONDUCTOR_CONFIG_DIR, CONDUCTOR_DATA_DIR, CONDUCTOR_STATE_DIR, CONDUCTOR_CACHE_DIR.

• Resolution order is per-kind env var, --home, CONDUCTOR_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, data.db, 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.

• Run conductor-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": {
      "conductor": {
        "command": "conductor-pp-mcp",
        "env": {
          "CONDUCTOR_HOME": "/srv/conductor"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use CONDUCTOR_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 CONDUCTOR_HOME, or doctor will not find credentials left under the former root.

Automatic learning

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.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, run:

conductor-pp-cli recall "<user's question>" --agent

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>", "conductor-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.

Step 2: decision tree

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 `conductor-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; conductor-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.

Step 3: always read warnings

• low_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 conductor-pp-cli sync to refresh entity lookups.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.