Borrowing it
Nothing to install: this file belongs to jhd3197/CachiBot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jhd3197/CachiBot/main/.claude/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/jhd3197/CachiBotWrote 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.
[](https://agentmods.dev/skills/jhd3197/cachibot/code-review)<a href="https://agentmods.dev/skills/jhd3197/cachibot/code-review"><img src="https://agentmods.dev/badge/skills/jhd3197/cachibot/code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jhd3197/cachibot/code-review"><img src="https://agentmods.dev/badge/skills/jhd3197/cachibot/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01837 |
| Opus 5.5 | $0.00022 | $0.00735 |
| Sonnet 5.5 | $0.00011 | $0.00367 |
| Haiku 4.5 | $0.00006 | $0.00184 |
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 2mo 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — 8-Agent Sweep
Run a full-codebase audit of CachiBot using 8 parallel review agents. Each agent focuses on a specific quality concern and reports findings with file paths and line numbers. Results are compiled into a single dated report.
Instructions
- Note today's date for the report header.
- Spawn all 8 review agents in parallel using the Task tool (subagent_type:
Explore). Each agent scans its focus area and returns findings rated Fix, Improve, or Note. - After all agents complete, compile their findings into a single report file at
.reviews/YYYY-MM-DD-review.md(create the.reviews/directory if it doesn't exist). - Print a summary to the user with totals per severity.
Agent Definitions
1. Tina — The DRY Enforcer
Scope: cachibot/ and frontend/src/
Looks for: Duplicated logic, copy-pasted code, missed shared abstractions
- Functions or blocks that appear in 2+ files with identical or near-identical logic (same body, different name counts)
- Pydantic models in
models/that share 80%+ of their fields — candidates for a base class - Repeated inline patterns: .env read/write, response formatting, validation checks, error response construction
- React components that duplicate rendering logic instead of extracting a shared component
- Zustand stores with duplicated fetch/loading/error patterns that could use a shared factory or helper
- Constants or config values hardcoded in multiple places instead of a single source of truth
2. Marcus — The Security Auditor
Scope: Full codebase Looks for: Auth gaps, injection vectors, data leaks, OWASP top 10
- Endpoints missing auth dependencies (
Depends(get_current_user)or role checks) — every route should require auth unless explicitly public - Route guards on the frontend — can a non-admin navigate to admin pages by typing the URL directly?
- Injection risks in any string interpolation touching .env files, database queries, shell commands, or file paths
- API keys or secrets that could leak in response payloads, error messages, or logs
- CORS configuration — is it locked to expected origins or wide open?
- WebSocket auth — does the WS handshake validate tokens the same way REST endpoints do?
- Hardcoded secrets, tokens, or passwords anywhere in the codebase
- File operation paths — can user input escape the workspace sandbox?
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.
- 2mo ago First seen · 204 lines · 56 tokens per session scan A 884c03311882
code-review is a skill published in the GitHub repository jhd3197/CachiBot (21 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 1,837 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
security-review
Complete a security review of the pending changes on the current branch.
code-review
Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's recipe covers them) at the effort level given first, before any target (low|medium|high|xhigh|max: from few high-confidence findings to many, some uncertain; ultra: deep…
simplify
Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.
ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
security-audit
Answer security questions about code, review a file or change for vulnerabilities, or run a full multi-agent audit of a codebase with a coverage ledger and independently verified findings.
security-diff-scan
Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other Git-backed change set.