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.
npx agentmods add commands/gosha70/code-copilot-team/review-decidegit clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/gosha70/code-copilot-team/review-decide)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/review-decide"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/review-decide.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00911 |
| Opus 5 | $0.00000 | $0.00456 |
| Sonnet 5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
review-decide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve a circuit breaker in the review loop. Accepts exactly one argument: approve, reject, or retry.
Usage
/review-decide approve
/review-decide reject
/review-decide retry
Prerequisites
- A live breaker: either
.cct/review/breaker-tripped.jsonexists, or an unresolvedreview_breakerescalation exists for THIS feature (bound via.cct/review/state.json'sfeature_id) — a crash can park the run without ever writing the breaker file (#233) - This command is run by the human, not the agent
Steps
1–3. Validate, Decide, Record — run the deterministic core
Resolve the helper — this command is installed globally and runs in arbitrary target projects, so the repo-relative path is only a fallback for sessions inside a CCT checkout:
HELPER="$HOME/.claude/scripts/review-decide.sh" # installed by setup.sh
[ -f "$HELPER" ] || HELPER="${CCT_REPO_DIR:-.}/scripts/review-decide.sh"
bash "$HELPER" <project-dir> <approve|reject|retry>
If neither location has it, say so and point at
adapters/claude-code/setup.sh --sync rather than improvising the state
transitions by hand.
The script owns every state transition that must not depend on prompt-following (#233):
- Breaker file present →
breaker_typeis read from it. - Breaker file missing → the context is RECONSTRUCTED, bound to THIS
feature via
.cct/review/state.json'sfeature_id(never a scan of other features' ledgers): the newest unresolvedreview_breakerescalation under.cct/auto-build/<feature_id>/escalations/supplies it (breaker_type: runner_crash_legacyforreview runner exited <n>details,reconstructedotherwise), andreconstructed_fromprovenance is recorded indecision.json— the driver validates it against the escalation it resolves on--resume. A corrupt record, a missingfeature_id, or no unresolvedreview_breakerescalation refuses with the precise reason; "Nothing to decide" is only said when no unresolvedreview_breakerescalation exists for this feature. - retry → the script bumps
attemptand resetsloop_start(mandatory in reconstruction mode too — a staleloop_starttrips the review loop clock before the next reviewer runs). breaker-tripped.jsonis removed after the decision is recorded.
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.
- 3d ago First seen · 81 lines · 0 tokens per session scan A 94c26e57f6bb
review-decide is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 911 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.