Collect and resolve selected findings in one pass, then verify; bare PR targets use online items, while PR +review authorizes matching review evidence and any needed review step.

Read local codemap telemetry logs and produce a diagnostic/usage report. Supports date filtering, session filtering, and optional anonymization before sharing. TRIGGER when: analyse recent codemap usage, debug query patterns, investigate errors, or prepare a shareable anonymized report of how codemap skills and CLI are being used.

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}" python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" --persist research-shared --emit agent-resolution.md || exit 1 # timeout: 5000 — cold resolve; every later site reads the research-shared sentinel instead of re-running python

Create, update, or delete agents, skills, and rules; update or delete hooks (hook creation not yet implemented — edit `hooks/<name>.js` directly). Full cross-reference propagation. Trivial edits (typos, small fixes ≤10 words) applied inline without agent; `.md` content-edits delegated to foundry:curator; `.py` and hook `.js` (under `hooks/`) edits delegated to foundry:sw-engineer, other code files (`.ts`, non-hook `.js`, `.sh`) edited inline and flagged as having no owning agent; large cross-ref fan-outs (> 3 files) also delegate. The parent orchestrates MEMORY.md, README, audit, calibration, and the final report. Also manages settings.json permissions atomically with permissions-guide.md. NOT for: validation/quality audit of existing agents/skills (use /foundry:audit); implementing application source code changes outside `.claude/` (use develop:feature or develop:fix — requires `develop` plugin).

`$codemap-py:rename-refs`: rename Python names; skip non-Python/unbuilt/local/grep/split/pkg-dir.

Run a bounded adversarial convergence loop with independent challengers and a strict-decrease stop rule.

Check opencode-rig install health and report exact remediation steps.

Execute a frozen plan or bounded change, run configured gates, and produce an evidence-backed commit handoff.

Produce a frozen implementation plan with owned paths, configured gates, risks, and acceptance criteria.

Build a source-backed research brief with labeled claims, contradictions, and explicit limits.

Review the current diff, a commit, or a path with independent read-only reviewers and a validated findings artifact.

`$codemap-py:scan-codebase [flags]` only: Python index; never auto-invoke; skip query/integration.

`$codemap-py:test-impact qname [--no-mocks]`: affected tests; skip caller/dependency query/exec.

find "$HOME/.claude/plugins/cache" -mindepth 2 -maxdepth 2 -type d 2>/dev/null | while IFS= read -r p; do m="${p%/*}"; m="${m##*/}" python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_foundry}/bin/resolve_plugin_root.py" --plugin-name "${p##*/}" --marketplace "$m" 2>/dev/null | sed "s|^|PLUGIN_ROOT: ${p##*/} |

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}" _CM_PROJ=$(git rev-parse --show-toplevel 2>/dev/null | xargs basename 2>/dev/null || echo "cm")