Borrowing it
Nothing to install: this file belongs to martin-francois/symphony-trello. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/martin-francois/symphony-trello/main/.codex/skills/review-sweep/SKILL.mdgit clone --depth 1 https://github.com/martin-francois/symphony-trelloWrote 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/skills/martin-francois/symphony-trello/review-sweep)<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/review-sweep"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/review-sweep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/review-sweep"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/review-sweep.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.01720 |
| Opus 5 | $0.00023 | $0.00860 |
| Sonnet 5 | $0.00009 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
review-sweep 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 12d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Sweep
Goals
- Find the PR related to the current Trello card or branch.
- Gather top-level comments, inline review comments, review states, and checks.
- Gather GitHub review threads, including whether each thread is resolved.
- Treat actionable human, bot, and Codex review feedback as blocking until handled.
- Reply to addressed GitHub review threads, but leave thread resolution to the reviewer unless the user explicitly asks you to resolve them.
- Reply in the right place when accepting, clarifying, or pushing back.
- Keep PR title, body, branch, and metadata aligned with the current Trello scope when an existing PR is reused.
- Record the outcome in the Trello workpad before handoff.
Finding The PR
Try these sources in order:
-
PR URLs in the Trello card description.
-
PR URLs in recent Trello comments.
-
Branch names in the Trello card description or comments.
-
The current branch:
git branch --show-current gh pr view --json number,url,title,state,headRefName,baseRefName -
Open PRs whose branch, title, body, or labels match card context:
gh pr list --state open --json number,url,title,body,headRefName,labels
If no PR exists, skip GitHub review checks and continue with local validation.
Feedback Sweep
For a PR number:
pr_number="<number>"
gh pr view "$pr_number" --json number,title,state,mergeable,reviewDecision,statusCheckRollup
gh api "repos/{owner}/{repo}/issues/$pr_number/comments"
gh api "repos/{owner}/{repo}/pulls/$pr_number/comments"
gh api "repos/{owner}/{repo}/pulls/$pr_number/reviews"
gh pr checks "$pr_number"
Also fetch review threads through GraphQL when the repository supports them. Paginate the review-thread connection so large PRs do not silently omit feedback:
owner="$(gh repo view --json owner --jq .owner.login)"
repo="$(gh repo view --json name --jq .name)"
gh api graphql --paginate \
-f owner="$owner" \
-f repo="$repo" \
-F number="$pr_number" \
-f query='
query($owner: String!, $repo: String!, $number: Int!, $endCursor: String) {
repository(owner: $owner, name: $repo) {
pullRequest(number: $number) {
reviewThreads(first: 100, after: $endCursor) {
pageInfo { hasNextPage endCursor }
nodes {
id
isResolved
isOutdated
path
line
comments(first: 100) {
nodes {
id
body
author { login }
createdAt
}
}
}
}
}
}
}'
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.
- 12d ago First seen · 210 lines · 47 tokens per session scan A 55245fe6b8c6
review-sweep is a skill published in the GitHub repository martin-francois/symphony-trello (2 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 1,720 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
moai-ref-cross-model-audit
Cross-model audit convergence reference for the plan-auditor and sync-auditor agents. Documents how to invoke the auditmulti MCP tool to fan a code review out across the codex and GLM (z.ai) backends in parallel, converge their verdicts with the in-session Claude verdict, and fold the resulting per-backend verdicts +…
codebase-sync
Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.
moai-foundation-quality
TRUST 5 quality principles and how MoAI enforces them through agents, the 3-level harness, /moai gate, and sync-auditor scoring. Use for code review, quality gate checks, coverage targets, or TRUST 5 compliance.
code-review-patterns
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
code-review-orchestration
6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.
code-review-pipeline
Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.