code-review

A code-review guide for changes that cross modules or affect security, payments, data, or public interfaces.

In plain words
What is it for?
It guides reviews of correctness, requirements, security, simplicity, and style, with attention to high-risk changes and independent review when useful.
Why use it?
It gives reviewers a priority order so crashes, missing requirements, and security problems are addressed before style concerns.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/chipfighter/coding-discipline/code-review
Any agent
npx skills add chipfighter/coding-discipline --skill code-review
Clone the repo
git clone --depth 1 https://github.com/chipfighter/coding-discipline

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00104 $0.00614
Opus 5 $0.00052 $0.00307
Sonnet 5 $0.00021 $0.00123
Haiku 4.5 $0.00010 $0.00061

Measured 2d ago against content hash d5c1131268cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review 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 2d 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.

plugins/coding-discipline/skills/code-review/SKILL.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performing a review (review it yourself; delegate when worthwhile and supported)

When an independent perspective is needed and the current client supports subagents, you may delegate a review. Give the reviewer carefully scoped context (what changed, which requirements it should meet, and the base..head diff range), not the entire session history. Review small changes yourself; do not add agent overhead for appearances.

Review in this priority order. Do not dwell on a lower priority while a higher one is unresolved:

  1. Correctness: is the logic sound; are edge cases, errors, or concurrency missing; can it crash?
  2. Requirements: check each requirement and design point. Does the change do what was requested, and is anything missing?
  3. Security: injection, unauthorized access, secret leakage, unvalidated input.
  4. Simplicity: overengineering, duplication, removable dead code, features that are not needed yet.
  5. Style: naming, consistency, readability—review these last, not first.

Use severity: fix blockers (crashes/security) immediately, fix important issues before proceeding, and note minor issues for later.

Receiving review feedback

  • Verify before changing anything: does this feedback apply to this codebase? Could it break existing behavior? Is there a reason the code is written this way? If uncertain, say, "I cannot verify X. Should I investigate, ask, or leave it for now?"
  • Do not comply blindly: if a suggestion is wrong, lacks context, asks for something not needed yet, or conflicts with an established architecture decision, push back with technical reasons rather than changing it because a reviewer said so. Stop and consult someone when the conflict concerns architecture.
  • No performative agreement: do not say "You're right!", "Good suggestion!", or "Thanks for catching that!" If you make the change, state what changed and where. If your pushback was wrong, say only, "I checked and I was wrong because X; I changed it." Do not write a long apology.
  • If anything is unclear, clarify every item before making changes. Do not act only on the items you understand; review items are often related, and partial understanding leads to wrong changes.
  • Address one item at a time, test each change, and confirm that it introduced no regressions (see verify-before-done).

Read the full file on GitHub · 25 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. 2d ago First seen · 25 lines · 104 tokens per session scan A d5c1131268cc

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository chipfighter/coding-discipline (6 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 614 once invoked, about $0.0005 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

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

office-hours

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…

GCWing/BitFun · 168 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

echo

Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.

cwinvestments/memstack · 35 tokens