add-dep
CommandVet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.
Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.
> /plugin marketplace add arbiterForge/codeArbiter
description: Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store. argument-hint: "[--stage N] [--greenfield|--brownfield] | --check"
Stand up the root-level `.codearbiter/` project-state store that opts a repo into arbiter management. This is the v2 replacement for vendoring/`init-vendor`: no symlinks, no shims, no dual root. It writes the activation flag and the empty state files, then hands off to the populator.
`.codearbiter/CONTEXT.md` frontmatter `arbiter: enabled` is the single activation flag — it gates {{IF:claude}}both the SessionStart persona injection and the arbiter statusline segments{{ELSE}}the SessionStart persona injection{{END}}. The scaffolded `CONTEXT.md` is a **stub** (no initialization sentinel), so after scaffolding the project still needs populating before normal operation.
<!-- catalog-command-modes:start -->
<!-- command-mode:--greenfield legacy-route:decompose --> `--greenfield` selects the exact `{{PLUGIN_ROOT}}/commands/decompose.md` workflow.
<!-- command-mode:--brownfield legacy-route:create-context --> `--brownfield` selects the exact `{{PLUGIN_ROOT}}/commands/create-context.md` workflow. That workflow populates an uninitialized stub. For an initialized brownfield project, keep the existing marker and route source-observed acquisition and target/delta work to `{{CMD:decompose}}` instead of replaying initial population. An initialized refresh of existing context facts uses `{{CMD:status}} drift` and the `context-check` owner after an explicit scoped or full selection.
Confirm the intended repository, existing state, selected outcome and actual host permissions before activation. Scaffolding enables governance and may install Git hooks; it does not prove context correctness or host enforcement. For existing source, use bounded inspection and the safe installed context writer in `{{PLUGIN_ROOT}}/skills/context-creation/SKILL.md`. Scoped agents are optional. Ordinary native Windows work does not require a special scout sandbox, profile attestation or per-document artifact approval.
If a real host permission or the installed safe writer is unavailable, report the exact operation and retain current state. Continue independent authorized inspection; do not fabricate a profile, receipt, context document or initialized marker. Successful scaffold or `--check` output is inventory, not evidence that population or a live host probe completed.
The two flags are mutually exclusive and neither may combine with `--check`. `--stage N` may accompany one only while `.codearbiter/CONTEXT.md` is absent: after checking the repository and host permissions, scaffold at that stage, then enter the selected workflow. When an uninitialized stub already exists, skip the refusing scaffolder and enter the selected workflow directly. An initialized marker selects the initialized acquisition or refresh owner above; a source-shape mismatch retains the selected legacy workflow's BLOCK. Without an explicit strategy, continue with the unchanged auto-detection procedure below under the same repository and host permissions. <!-- catalog-command-modes:end -->
Before opening an active host session in an unfamiliar repository, a trusted external process may inspect an explicit directory with `python "{{PLUGIN_ROOT}}/hooks/init-codearbiter.py" --check --passive --root PATH`. This bounded read checks only that directory's `.codearbiter/CONTEXT.md` activation marker and prints a JSON inventory for Git hooks/exclusions, background Git fetch, update refresh, and inference transport. Every effect is `performed: false`, with capability `unverified` and authorization `not_established`. The root is caller supplied and unverified; no Git command, repository script, network request, global setting edit, or model source read occurs. Sensitive/excluded source paths must be inventoried separately before any model read. If an active host session has already started, this inspection cannot undo its earlier startup effects.
Activation is a separate step under the applicable host, network, repository-write, and inference permissions. The normal scaffold and active SessionStart behavior below remain in force for repositories that already opted in.
1. Run the scaffolder against the repo's git toplevel (resolved by the script):
python "{{PLUGIN_ROOT}}/hooks/init-codearbiter.py"It is idempotent and refuses if `.codearbiter/CONTEXT.md` already exists — it never overwrites state. Pass `--stage N` to set the initial maturity value (default `1`). Use `--check` to report state without creating anything.
2. The default creates `.codearbiter/` with `CONTEXT.md` (`arbiter: enabled`, `stage: N`, `context-format: html`, stub body), `open-questions.md`, `overrides.log` (audit header), `last-checkpoint` (`0`) and `.gitattributes` exact-byte rules. It does not create `open-tasks.md` or `done-tasks.md`. The HTML knowledge population step creates the native portable work project identity in the same transaction as the initialized marker. Until then, native work creation refuses; do not create a placeholder task or board. `--format markdown` retains the legacy Markdown documents and both task boards. An existing HTML project with a legacy board stays legacy until explicit adoption. See `{{PLUGIN_ROOT}}/includes/knowledge.md`.
3. **Then route to the populator** — the stub is not yet usable:
read the codebase and synthesize the full context, writing the initialization sentinel).
The populator is **mandatory, not optional**: it authors `tech-stack.md`, `coding-standards.md`, and `s
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…
Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.
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.