code-review

A code-review workflow for the Psyche Build repository. It examines requested changes for real defects and risks without editing files or changing GitHub state.

In plain words
What is it for?
Use it to review working-tree changes, staged files, commits, commit ranges, branches, pull requests, patches, regressions, or implementations.
Why use it?
It focuses reviews on bugs that the change may introduce, instead of spending time on style preferences or unrelated existing issues.

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/opencoven/psyche-build/code-review
Any agent
npx skills add OpenCoven/psyche-build --skill code-review
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/psyche-build

Made for: Claude Code, Codex.

Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,584 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 $0.00132 $0.03584
Opus 5 $0.00066 $0.01792
Sonnet 5 $0.00026 $0.00717
Haiku 4.5 $0.00013 $0.00358

Measured 2d ago against content hash 84a5c24fed2d, 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.

.github/skills/code-review/SKILL.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Psyche Build code review

Operating contract

Review the requested change without editing files, applying patches, committing, pushing, merging, or mutating GitHub state.

Find defects introduced or exposed by the reviewed change. Do not report style preferences, optional refactors, speculative hardening, unrelated pre-existing problems, or missing tests unless a concrete behavior is unprotected and can fail.

Treat explicit requests to find exploitable vulnerabilities as security-review tasks instead. During an ordinary code review, still inspect authentication, authorization, filesystem, process, browser, and secret-handling boundaries when the changed behavior crosses them.

1. Establish the exact review target

Identify what the user asked to review before reading implementation details:

  • Working tree: inspect git status --short, unstaged changes, staged changes, and every relevant untracked file.
  • Staged changes: use the index as the target; do not mix in unstaged work.
  • Commit: inspect that commit and its parent relationship. Do not assume HEAD^ is the intended target when a commit hash was supplied.
  • Range: preserve the user's endpoints and whether the range is two-dot or three-dot.
  • Branch: resolve the intended base, compute the merge base, and review the branch delta rather than unrelated local dirt.
  • Pull request: inspect PR metadata, base/head refs, changed files, and the actual diff. Prefer gh when remote context is required.

State a material base ambiguity rather than silently choosing a comparison that could change the result. Never omit untracked files from a working-tree review.

Start with a change inventory:

git status --short
git diff --stat
git diff --name-status
git diff --cached --stat
git diff --cached --name-status

Adapt these commands to the target. Disable pagers for Git and GitHub commands. Do not run destructive or mutating commands.

2. Recover intent before judging behavior

Read the full file on GitHub · 398 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 · 398 lines · 132 tokens per session scan A 84a5c24fed2d

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository OpenCoven/psyche-build (2 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 3,584 once invoked, about $0.0007 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.