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 damianvtran/local-operator --skill code-reviewgit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/code-review)<a href="https://agentmods.dev/skills/damianvtran/local-operator/code-review"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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/damianvtran/local-operator/code-review"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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 | $0.00045 | $0.00692 |
| Opus 5.5 | $0.00018 | $0.00277 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
The same practice for any agent: reviewing a diff, a patch, or another agent's work.
Read the diff first
git diff <base>..<head>(or the PR's diff) IS the review. Read the tree only where the diff raises a question you can state.- Open a file when you can name the question it answers; re-reading files you already read is waste.
- Review what changed plus what it touches: callers, shared state, and the tests near the change.
Classify every finding
| Severity | Means |
|---|---|
| BLOCKER | Wrong, unsafe, or loses data. Ship it and something breaks. |
| MAJOR | A real defect or missing case that will bite, but not stop-ship. |
| MINOR | Correctness-preserving improvement. |
| NIT | Style, naming, wording. |
- Caps: at most 5 MINOR and 5 NIT per round, the highest-value ones. A long tail of nits buries the blockers and costs a remediation round to answer.
- Severity is about consequence, not effort to fix. Do not inflate; do not deflate to avoid an awkward round.
Evidence over inference
- Every finding carries a location: file, line, and the code path. Without one it is a lead, not a finding.
- Reproduce cheaply where possible: the targeted test, the query, a tiny probe. A finding you reproduced outranks one you reasoned to.
- Where you cite a number or status, derive it or name its source. A value read from a summary is a lead.
- Say plainly when nothing blocks. Padding a report to look thorough is a failure mode; so is agreeing to be agreeable.
Remediation rounds (round 2 and later)
- Scope to the delta:
git diff <previous_reviewed_head>..<current_head>. Verify the fixes; do not re-audit unchanged, previously approved files. - No new out-of-scope findings; note them as follow-ups instead.
- A fix that unexpectedly touches more is in scope again: check its blast radius.
- A genuine late BLOCKER/MAJOR with a reproduced code path stays admissible; delta scope is not a waiver for correctness, security or regression risk.
- Collect all initial review streams before ONE remediation commit; see
guide://deliveryfor compatibility proof and metadata-only addenda.
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.
- 3d ago Changed · +4 lines 2147f8a67d7b
- 5d ago First seen · 53 lines · 45 tokens per session scan A 190db6c4a9e2
code-review is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 692 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
coding-standards
Applies language-neutral engineering standards when writing or reviewing code, especially around boundaries, failures, domain models, dependencies, tests, and type safety.
hqe
Comprehensive codebase health auditing, remediation, and verification skill based on the canonical HQE Protocol v5.0.0.
code-reviewer
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
requesting-code-review
Use when completing tasks, implementing major features, or before merging. Validates work meets requirements through systematic review process.