Codex Rig

Plugin codex-rig in Borda/AI-Rig. Commands read from the repo's manifest — today.

Skills (16)

• agent-shims

  Safely manage Codex Rig role-agent shims: doctor, status, or remove; install only reports its platform block. One action only.

• assess

  Analyze issue/PR/problem before implementation; produce source-backed findings and measurable gates. Skip diff or PR correctness reviews owned by code-review and symptom-first debugging owned by investigate.

• audit

  Audit Codex configuration, workflow contracts and prompt efficiency; optionally discover overlapping instruction intent and propose advisory consolidation with preserved obligations and loading scope. Skip measured skill/role recall, precision and confidence-accuracy scoring owned by calibrate.

• calibrate

  Calibrate skills/role cards for leaks/gaps with recall, precision, and confidence-accuracy checks. Skip configuration and workflow-contract audits owned by audit.

• challenge-resolve

  Independently review and fix a bounded task through convergence rounds, with evidence-backed closure and explicit stop/remediation decisions. Use only when the user explicitly requests an adversarial review-and-fix loop over an existing implementation, feature, problem, or diff; not for ordinary rev

• code-remediate

  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.

• code-review

  Review local diffs and PRs with specialists and JSON artifacts, or screen an open PR at an evidence gate and advise whether to close it; read-only, never writes to GitHub. Skip pre-implementation problem assessment owned by assess and symptom-first debugging owned by investigate.

• implement

  Implement changes with a linear plan-build-verify workflow and measurable quality gates.

• investigate

  Investigate code debugging and root-cause narrowing; use measurable gates before fixes. Skip general issue or PR assessment owned by assess and diff or PR correctness reviews owned by code-review.

• kaggle

  Build/extend grounded Kaggle Jupytext notebooks for training, EDA, inference, or resume workflows, grounding schema and submission format through the authenticated kaggle CLI.

• manage

  Manage Codex agents, skills, or config entries: create, update, or remove with guardrails.

• optimize

  Optimize a measurable metric with bounded iterations, resumable numeric campaigns, isolated ablations, and descriptive retrospectives.

• profile

  Explain native Codex session and agent token usage, inclusive tool time, and optional supplied-rate cost estimates from selected telemetry; excludes application CPU/GPU profiling and billing statements.

• release

  Draft release notes, changelogs, contributor credits, migration guides, and summaries from traced unreleased changes; assess SemVer readiness without publishing.

• research

  Research docs, papers, or state of the art; provide source-backed recommendations and caveats.

• sync

  Dry-run active plugin cache drift; refresh/reinstall only with approval; keep shims separate.

Hooks (2)

• SessionStart

  "$PLUGIN_ROOT/bin/python" "$PLUGIN_ROOT/hooks/session_start.py"

• Stop

  "$PLUGIN_ROOT/bin/python" "$PLUGIN_ROOT/hooks/review_stop.py"

Similar plugins