agentenv: Skill for Claude Code

.claude/skills/review-and-fix/SKILL.md

review-and-fix is a skill for Claude Code from eduardoarantes/agentenv. It costs 85 tokens per session (2,026 once invoked), scanned A, original, MIT.

A workflow for reviewing the current code branch, recording findings in a tracker file, selecting issues with the user, and applying chosen fixes in separate commits.

In plain words
What is it for?
Use it when you want to review code, track actionable problems, choose which ones to address, and commit the fixes individually.
Why use it?
It turns a review into a traceable fix process, so findings are not lost and each selected change remains isolated.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool.

This is eduardoarantes/agentenv's own configuration. It tells Claude Code how to work on agentenv 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 agentenv configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eduardoarantes/agentenv. 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/eduardoarantes/agentenv/main/.claude/skills/review-and-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/eduardoarantes/agentenv

Made for: Claude Code.

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-and-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/eduardoarantes/agentenv/review-and-fix.svg)](https://agentmods.dev/skills/eduardoarantes/agentenv/review-and-fix)
Your own site
<a href="https://agentmods.dev/skills/eduardoarantes/agentenv/review-and-fix"><img src="https://agentmods.dev/badge/skills/eduardoarantes/agentenv/review-and-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,026 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 $0.00085 $0.02026
Opus 5 $0.00043 $0.01013
Sonnet 5 $0.00017 $0.00405
Haiku 4.5 $0.00009 $0.00203

Measured 8d ago against content hash be092fcdee1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-and-fix 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 8d 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.

.claude/skills/review-and-fix/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review and fix

Drives a code review through to applied commits. The flow has four phases — review, track, select, fix-loop. Each fix runs in a fresh sub-agent so context never bleeds between items.

Phase 1 — run the review

  1. Capture a timestamp once and reuse it for the tracker filename. Use UTC, YYYYMMDDTHHMMSSZ format (filesystem-safe, sortable). Example: 20260514T103000Z.
  2. Collect minimal branch context in parallel (single tool message):
    • git branch --show-current
    • git rev-parse --abbrev-ref --symbolic-full-name @{u} 2>/dev/null || true (upstream — may be empty)
    • git log -1 --format=%H (HEAD sha at start of run)
  3. Invoke the built-in review skill via the Skill tool: Skill(skill="review"). The review output appears in this conversation — treat it as the source of truth for findings.
  4. Refuse to proceed if the review skill reports no findings or only informational/positive notes (nothing actionable). Say so and stop — don't fabricate items to fix.

Phase 2 — build the tracker

Write .agentenv/review-<timestamp>.md using the structure below. The file is the single source of truth for run state: the orchestrator re-reads it before each fix and updates it after each fix.

# Code Review Fix Run

- **Branch:** <branch>
- **Upstream:** <upstream or "(none)">
- **Started:** <ISO 8601 UTC>
- **HEAD at start:** <sha>
- **Review skill:** /review

## Summary
- Total: <n>
- Selected: <n>
- Fixed: <n>
- Failed: <n>
- Skipped: <n>
- Pending: <n>

## Items

### 1. <short title — 6–10 words>
- **Status:** pending
- **Severity:** high | medium | low | nit
- **File:** <path>:<line> (or "multiple")
- **Issue:** <1–3 sentences from the review>
- **Suggested fix:** <1–3 sentences — what the review proposed, or your read>
- **Commit:** —
- **Notes:** —

### 2. <…>
…

Rules for the tracker:

  • One item per concrete, atomic fix. If the review bundles unrelated problems into one bullet, split them into separate tracker items.
  • Skip items that are purely "consider …" / "you might want to …" with no clear action. Note them in a final ## Deferred section instead.
  • Use forward slashes in paths (cross-platform — same rule as the rest of this repo's canonical artifacts).
  • .agentenv/ is already gitignored, so the tracker stays local. Don't add a separate .gitignore entry.

Read the full file on GitHub · 178 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. 8d ago First seen · 178 lines · 85 tokens per session scan A be092fcdee1b

Subscribe to this mod's changes

review-and-fix is a skill published in the GitHub repository eduardoarantes/agentenv (5 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 2,026 once invoked, about $0.0004 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.