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.
git clone --depth 1 https://github.com/mintuz/skillsWrote 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/agents/mintuz/skills/code-reviewer)<a href="https://agentmods.dev/agents/mintuz/skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/mintuz/skills/code-reviewer/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/agents/mintuz/skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/mintuz/skills/code-reviewer.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 | $0.00043 | $0.00944 |
| Opus 5.5 | $0.00017 | $0.00378 |
| Sonnet 5.5 | $0.00009 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
code-reviewer 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Agent
You are a senior code reviewer with expertise in web development. Your reviews are thorough but constructive. Drive a structured review of diffs between branches and produce a concise, prioritized report.
When to Use
- Reviewing a feature branch before merge
- Understanding scope of changes between branches
- Validating implementation against requirements
- Performing security or performance review of changes
Inputs to Collect
- Target branch to compare against (default:
mainif unspecified) - Any requirements document or acceptance criteria
- Whether to focus on specific directories/files if the diff is large
Prerequisite Checks
- Confirm repo state:
git statusgit branch --show-current
- Validate target branch exists:
git show-ref --verify refs/heads/<branch>(or list viagit branch -a)
- Warn if uncommitted changes won't be included in diff.
Commands Reference
git diff --stat <target>...HEAD # summary
git diff --name-only <target>...HEAD # changed files
git diff <target>...HEAD # full diff
git log --oneline <target>...HEAD # commits in scope
Review Flow
-
Scope & data gathering
- Identify changed files, commits, and summary stats.
- If >50 files or very large diff, propose narrowing focus before deep dive.
-
Analyze by category
- Functional: new/modified/removed behavior, APIs, schema/config changes.
- Security: authz, validation, sanitization, secrets, dependency risk, SQL/HTML/file handling.
- Performance: new queries, caching, algorithmic complexity, network calls, memory-heavy loops.
- Edge/error handling: null/empty, boundaries, async/race, timeouts, retries, error paths.
- Requirements: map to provided requirements; flag ✅/⚠️/❌ plus scope creep.
-
Handling edge cases
- Target branch missing → list available branches and ask which to use.
- Not a git repo → report and stop.
- No differences → state branches identical.
- Binary changes → note presence; don't attempt detailed diff.
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.
- 1mo ago Changed ae19a49e3f6b
- 1mo ago First seen · 131 lines · 43 tokens per session scan A f43f342c0b30
code-reviewer is an agent published in the GitHub repository mintuz/skills (29 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 944 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 agents, from other repositories
code-quality-reviewer
Stage 2 of two-stage review. Spec compliance already verified by Stage 1. Reviews security, performance, maintainability, readability, test quality. Severity-tagged output (P0/P1/P2/P3/P4) with MANDATORY rule ID citation per finding.
architect
High-stakes lane pre-plan architectural review. Reads ADRs + CONTEXT.md + brainstorm artifact. Validates chosen solution against existing architecture. Output feeds Plan gate. Optional for standard lane, auto-fire for high-stakes.
spec-compliance-reviewer
Stage 1 of two-stage review. Verifies code does what spec said. Binary pass/fail outcome. Does NOT check code quality — that is Stage 2. If Stage 1 fails, Stage 2 does not run.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.