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 skills add mochow13/keen-code --skill reviewgit clone --depth 1 https://github.com/mochow13/keen-codeWrote 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/mochow13/keen-code/review)<a href="https://agentmods.dev/skills/mochow13/keen-code/review"><img src="https://agentmods.dev/badge/skills/mochow13/keen-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/mochow13/keen-code/review"><img src="https://agentmods.dev/badge/skills/mochow13/keen-code/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.00661 |
| Opus 5.5 | $0.00008 | $0.00264 |
| Sonnet 5.5 | $0.00004 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
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 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Skill
Review focus (optional): $ARGUMENTS
Steps
-
Gather change context. Run in parallel:
git status --shortgit diff --stagedgit diffgit ls-files --others --exclude-standardgit log -n 3 --oneline
Review both staged and unstaged changes. Treat untracked files as relevant when they appear related to the user's request, and open them directly because
git diffwill not show their contents. -
Read project conventions. If
AGENTS.md,CLAUDE.md, orCONTRIBUTING.mdexist at the repo root, read them before judging the diff. -
Inspect the changed code. Open the files and surrounding code needed to verify behavior. Do not rely only on the diff when control flow, data shape, or tests depend on nearby context.
-
Review against these checks:
Correctness
- No behavior regressions, missed edge cases, or undefined references
- Error handling matches the risk and existing project patterns
- Public contracts, CLI behavior, file formats, and compatibility are preserved unless the user asked to change them
- Imports, variables, or functions made unused by the changes are removed
Surgical Changes
- Every changed line traces to the user's request
- No "improvements" to adjacent code, comments, or formatting
- No refactored code that wasn't broken
- No deleted pre-existing dead code unless explicitly asked
Simplicity
- No speculative features or abstractions
- No unnecessary configurability
- No error handling for impossible scenarios
- Functions are as short as they can be while remaining clear
Testing
- Critical paths have tests
- New functionality is exercised by tests
- Existing tests still cover the changed behavior
- Relevant tests pass, or any unrun tests are called out with the reason
Style
- Matches existing naming and patterns
- Minimal comments (only when strictly necessary)
- Language-specific formatting applied (e.g.,
gofmt)
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 First seen · 88 lines · 21 tokens per session scan A 05cf61454f15
review is a skill published in the GitHub repository mochow13/keen-code (72 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 661 once invoked, about $0.0001 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
code-review
Review a git diff (or working-tree changes) like a senior engineer — correctness, security, performance, readability — and return a verdict plus structured, line-anchored findings.
tlamatini-planner-trace-replay
Replay the most recent global execution planner trace from tlamatini.log and explain why each capability got the score it did.
parity-guard-test-pattern
When checking that all callers of a contract implement it correctly, you get false positives from wrapper delegators.
review-pr
Deeply review a GitHub pull request.
write-e2e-test
Write an end-to-end (e2e) test for vix. Use when the user asks to add, create, or modify an e2e test that drives the real vix TUI and vixd daemon against the mock LLM server.
loop-verifier
Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.