review-submit

A command for submitting completed work to a peer-review process. It checks that the project is ready, starts or continues review rounds, and reports the review result.

In plain words
What is it for?
Checking the Git worktree, initializing or continuing review state, running review-round-runner.sh, and returning the peer-review verdict.
Why use it?
It prevents unfinished or uncommitted work from entering review and stops safely when peer review is disabled or a review circuit breaker has fired.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/gosha70/code-copilot-team/review-submit
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00926
Opus 5 $0.00000 $0.00463
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00093

Measured 2d ago against content hash 8a9f6e600646, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-submit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

adapters/claude-code/.claude/commands/review-submit.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Submit work for peer review. Validates clean worktree, initializes or continues the review loop, invokes review-round-runner.sh, and returns the verdict.

Prerequisites

  • CCT_PEER_REVIEW_ENABLED must be true (set by --peer-review launcher flag)
  • Working tree must have no uncommitted changes (except .cct/ review state)
  • jq must be installed

Steps

1. Validate Environment

Check that peer review is enabled:

  • If CCT_PEER_REVIEW_ENABLED is not true, inform the user and stop.

2. Validate Clean Worktree

Run git status --porcelain and check for uncommitted changes (excluding .cct/):

  • If dirty, tell the user: "Commit or stash your changes before submitting for review."
  • Do not proceed until the worktree is clean.

3. Check for Active Breaker

If .cct/review/breaker-tripped.json exists:

  • Read and display the breaker context to the user.
  • Tell the user: "A circuit breaker has fired. Run /review-decide approve|reject|retry to proceed."
  • Do not invoke the runner. Stop here.

4. Initialize or Continue State

If .cct/review/state.json does not exist, create it:

{
  "current_round": 0,
  "attempt": 1,
  "loop_start": <current-unix-timestamp>,
  "feature_id": "<from specs/*/plan.md or ask user>",
  "phase": "<plan|build — infer from current agent or ask>",
  "subject_provider": "claude",
  "peer_provider": "<from CCT_PEER_PROVIDER env or empty for profile default>",
  "review_scope": "<from CCT_PEER_REVIEW_SCOPE env or 'both'>",
  "target_ref": "<current git branch or HEAD>",
  "last_verdict": null,
  "findings": {}
}

If state.json already exists, the runner will read it and continue from the current round.

5. Invoke the Runner

Run review-round-runner.sh <project-dir> as a synchronous subprocess.

The runner exits with:

  • 0 = PASS — review passed. Read .cct/review/loop-summary.json and inform the user. Proceed to /phase-complete.
  • 1 = FAIL — review failed. Read .cct/review/findings-round-N.json (where N is the current round from state.json). Present each finding to the user. For blocking findings, address them (fix, dispute, defer, or mark not-applicable), write .cct/review/resolution-round-N.json, commit fixes, then run /review-submit again.
  • 2 = BREAKER — circuit breaker tripped. Read .cct/review/breaker-tripped.json and present the context. Tell the user to run /review-decide approve|reject|retry. Stop and wait.

Read the full file on GitHub · 100 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 100 lines · 0 tokens per session scan A 8a9f6e600646

Subscribe to this mod's changes

review-submit is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 926 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.