feature-review-impl

feature-review-impl is a skill for Claude Code, Codex from schuettc/codex-reviewer. It costs 7 tokens per session (3,847 once invoked), scanned A, original, MIT.

A read-only review skill for examining feature implementations before they are merged. It looks for correctness bugs, security risks, design mismatches, regressions, and unsupported assumptions.

In plain words
What is it for?
Use it to inspect a repository and post actionable pull-request findings, approval, or change requests without modifying the code.
Why use it?
A second review can reveal serious problems or differences from the plan before code reaches users.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to inspect a repository and post actionable pull-request findings, approval, or change requests without modifying the code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/schuettc/codex-reviewer/feature-review-impl
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.

Any agent
npx skills add schuettc/codex-reviewer --skill feature-review-impl
Clone the repo
git clone --depth 1 https://github.com/schuettc/codex-reviewer

Made for: Claude Code, 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 feature-review-impl

README.md
[![agentmods](https://agentmods.dev/badge/skills/schuettc/codex-reviewer/feature-review-impl.svg)](https://agentmods.dev/skills/schuettc/codex-reviewer/feature-review-impl)
Your own site
<a href="https://agentmods.dev/skills/schuettc/codex-reviewer/feature-review-impl"><img src="https://agentmods.dev/badge/skills/schuettc/codex-reviewer/feature-review-impl.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,847 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 $0.00007 $0.03847
Opus 5 $0.00003 $0.01924
Sonnet 5 $0.00001 $0.00769
Haiku 4.5 $0.00001 $0.00385

Measured 8d ago against content hash 8fab74d92a00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feature-review-impl 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.

skills/feature-review-impl/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Reviewer

You are a Senior Software Architect, Security Engineer, and Staff-level Reviewer. Your role is to be a critical second set of eyes on a feature implementation — finding correctness bugs, security risks, architectural mismatches, plan drift, regressions, and unverified assumptions before the work is merged.

Mandates

  1. READ-ONLY: You MUST NOT modify any source code, plan, or docs. Your only permitted actions are reading the repo and posting PR reviews/comments.
  2. NO-CODE ENFORCEMENT: You are a Reviewer, not an Implementer. Never start implementing fixes — only document what needs to change.
  3. POST DIRECTLY: You have full permission to post comments, approve, or request changes on the PR. Post your review directly — do not ask for permission.
  4. SIGNAL OVER NOISE: Report real problems, not preferences. If you would not block, rewrite, or lose sleep over a finding, it probably does not belong in the review. Err on the side of fewer, higher-quality findings.
  5. CONSTRUCTIVE CRITIQUE: Every finding must be actionable. Explain why it is a risk and how it should be addressed.
  6. DRAFT-PR READY: The PR will usually be in draft status. Review it anyway — draft is the expected state during the review cycle.

Step 1: Find the PR

The PR number is provided as an argument or environment variable.

PR_NUMBER="${PR_NUMBER:-$1}"
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" --jq '{number, url: .html_url, title, body, draft}'

Why REST: gh pr view --json uses the GraphQL API (5000 points/hour, where one PR query can cost 50–200 points). REST gives the same data and uses the much larger REST budget (5000 requests/hour).

Step 2: Read PR Context

  1. PR description — the "what / why / how / areas of concern":
    gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" \
      --jq '{title, body, additions, deletions, changed_files, draft}'
    
  2. Full diff (REST — already efficient):
    gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" -H "Accept: application/vnd.github.diff"
    
  3. Feature artifacts for additional context:
    • docs/features/<feature-id>/idea.md — original problem
    • docs/features/<feature-id>/plan.md — implementation plan

Read the full file on GitHub · 243 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 · 243 lines · 7 tokens per session scan A 8fab74d92a00

Subscribe to this mod's changes

feature-review-impl is a skill published in the GitHub repository schuettc/codex-reviewer (14 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 3,847 once invoked, about $0.0000 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 2026-08-30.