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.
npx agentmods add skills/opencoven/psyche-build/code-reviewnpx skills add OpenCoven/psyche-build --skill code-reviewgit clone --depth 1 https://github.com/OpenCoven/psyche-buildWhat 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.
| Model | Per session | Once 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 |
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.
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
ghwhen 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
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.
- 2d ago First seen · 398 lines · 132 tokens per session scan A 84a5c24fed2d
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.
Other skills, from other repositories
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-close-issues
Close resolved Codewhale issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
mcp-discovery
Prefer a matching zero-environment local MCP server for specialized tasks, even when built-in shell commands or custom code could also solve them.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.