add-dep
CommandVet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.
Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.
> /plugin marketplace add arbiterForge/codeArbiter
description: Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report. argument-hint: (none)
Periodic sweep of the entire codebase with the reviewer fleet, funneled to a single dated report. Surfaces findings — not a promotion gate, enforces no sign-off.
1. Build the unit list — the same fleet as `{{CMD:review}}`, scoped to the whole codebase against the `{{PROJECT_DIR}}/.codearbiter/` docs:
| Reviewer | Reads | |---|---| | `security-reviewer` | `security-controls.md`; reviews security posture | | `auth-crypto-reviewer` | `security-controls.md`; authn/crypto/key/secret paths | | `dependency-reviewer` | dependency manifests; license + supply-chain posture | | `migration-reviewer` | migration history; safety + classification | | `coverage-auditor` | test coverage vs. obligations across the tree | | `architecture-drift-reviewer` | `decisions/`; drift between code and accepted ADRs |
2. Route to `dispatching-parallel-agents` (`{{PLUGIN_ROOT}}/skills/dispatching-parallel-agents/SKILL.md`) with that unit list (read-only batch). It dedupes, then funnels through `finding-triage` → `verdict-aggregator` and returns the single read-only verdict. 3. After the verdict returns, separately dispatch `checkpoint-aggregator` with that verdict and the reviewed commit from `git rev-parse HEAD`, the UTC review-start time, and whether the reviewed worktree was dirty. Retain these observed values from before the sweep. It writes the dated report to `{{PROJECT_DIR}}/.codearbiter/checkpoints/YYYY-MM-DD.md`: findings by severity with file:line, and out-of-scope items marked inline `[NEEDS-TRIAGE]`. 4. Write the current override **count** to `{{PROJECT_DIR}}/.codearbiter/last-checkpoint` — the integer baseline the {{IF:claude}}statusline{{ELSE}}startup briefing{{END}} subtracts for its overrides-since-checkpoint counter. The value is the number of non-comment, non-blank lines in `overrides.log` at this moment (`0` if the log is absent). This re-zeros the `over:N` segment until the next `{{CMD:override}}`. Write a bare integer, not a timestamp — the {{IF:claude}}statusline{{ELSE}}briefing{{END}} treats any value above the current total as stale and falls back to showing every override. 5. Report the checkpoint path.
Read-only except writing the checkpoint doc and `last-checkpoint` — MUST NOT modify code. MUST NOT consume raw reviewer output — only the `finding-triage` → `verdict-aggregator` verdict. Checkpoint persistence MUST remain the separate `checkpoint-aggregator` step and MUST NOT run for `{{CMD:review}}` or another generic parallel batch. MUST NOT resolve a `[CONFIRM-NN]` surfaced during the sweep by guessing. The report surfaces findings; it does not block or sign off anything.
Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.
Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.
Inspect ADR health read-only; optionally select one ADR with --adr N.
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings…
Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.