symphony-trello: Skill for Codex

.codex/skills/review-sweep/SKILL.md

review-sweep is a skill for Codex from martin-francois/symphony-trello. It costs 47 tokens per session (1,720 once invoked), scanned A, original, Apache-2.0.

Instructions for collecting and addressing pull-request feedback before handing work to reviewers or merging it. A pull request is a request to review and add a branch's changes to another branch.

In plain words
What is it for?
Use them to find the relevant pull request, inspect feedback and checks, respond to issues, and record the review outcome on the Trello card.
Why use it?
They ensure comments, review threads, automated checks, and review status are all considered before work moves forward.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: mentions Codex.

This is martin-francois/symphony-trello's own configuration. It tells Codex how to work on symphony-trello itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything symphony-trello configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/martin-francois/symphony-trello/main/.codex/skills/review-sweep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/martin-francois/symphony-trello

Made for: Codex.

Wrote 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.

agentmods badge for review-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/martin-francois/symphony-trello/review-sweep/github.svg)](https://agentmods.dev/skills/martin-francois/symphony-trello/review-sweep)
Your own site
<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.

agentmods 80×15 button for review-sweep

Your own site · 80×15
<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>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00047 $0.01720
Opus 5 $0.00023 $0.00860
Sonnet 5 $0.00009 $0.00344
Haiku 4.5 $0.00005 $0.00172

Measured 12d ago against content hash 55245fe6b8c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

.codex/skills/review-sweep/SKILL.md · 210 lines

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:

  1. PR URLs in the Trello card description.

  2. PR URLs in recent Trello comments.

  3. Branch names in the Trello card description or comments.

  4. The current branch:

    git branch --show-current
    gh pr view --json number,url,title,state,headRefName,baseRefName
    
  5. 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
                }
              }
            }
          }
        }
      }
    }'

Read the full file on GitHub · 210 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. 12d ago First seen · 210 lines · 47 tokens per session scan A 55245fe6b8c6

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories