Resolve cq.yaml + CQ_CONFIG_JSON env into a single ResolvedConfig view. Returns project_root, cq_yaml_path, name, cmd, cfg, declared_metrics, output_dir. Read-only — does not create directories or mutate state.

Return project structure, entrypoint kind, contract state, and output evidence. Read-only.

Run static and contract validation before execution. Optional inline ExperimentPlan / ExperimentPlanSet validation. Read-only.

Run post-run validation gates (manifest / metrics / run_summary) on a completed output directory. Read-only.

Return a compact, decision-facts oriented summary of a RunRecord. Includes best/last metrics, validation status, lineage, artifact counts, decision_facts. Read-only.

Diff two RunRecords (or output dirs). Returns metric deltas, config changes, lineage relation, decision_facts. Read-only.

Walk a RunRecord's parent chain. Returns ordered nodes from this run back to its earliest reachable ancestor. Read-only.

Apply ExperimentPlan to project (modifies cq.yaml.configs only — never train.py). Provenance recorded under .pcq/plans/<plan_id>.json. Returns rejected envelope with reason='schema_invalid'|'validation_failed' on bad input.

Expand ExperimentPlanSet members into N output directories, each with its own cq.yaml + plan provenance. Returns rejected envelope with reason='schema_invalid'|'validation_failed' on bad input.

Scaffold a CQ-runnable experiment (cq.yaml + train.py contract script, optionally pyproject.toml + agent runtime assets).

Generate run_record.json + validation_report.json for an output directory. Walks ancestors to find project root if not provided. Writes to output_dir.

Install pcq agent runtime assets (AGENTS.md / CLAUDE.md managed block, .agents|.claude/skills/pcq/SKILL.md). Optionally write .mcp.json to wire pcq MCP server.

Inspect pcq agent runtime asset status (installed / missing / stale / divergent / unmanaged) without writing. Read-only.

Execute cq.yaml.cmd with auto-wired CQ_CONFIG_JSON env. Captures stdout/stderr to .pcq/run_*.log. For long-running GPU training, prefer the CQ service queue.