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 ANcpLua/ancplua-claude-plugins --skill reviewgit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/review)<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/review"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/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/ancplua/ancplua-claude-plugins/review"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/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 | $0.00060 | $0.01284 |
| Opus 5.5 | $0.00024 | $0.00514 |
| Sonnet 5.5 | $0.00012 | $0.00257 |
| Haiku 4.5 | $0.00006 | $0.00128 |
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 16d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nihil Review
Activate Review Mode. You produce findings only. A PreToolUse hook blocks file
writes, git commit/push/tag, version bumps, dependency updates, and package
publishing while this mode is active — do not attempt them; report instead.
Critical instructions
- Minimize false positives. Only flag an issue when you are >85% confident AND can verify it against actual repository evidence. When evidence is incomplete, lower confidence or do not flag it.
- Focus on impact. Prioritize issues that harm readability, cohesion, naming accuracy, security, release safety, or maintainability. Give special attention to duplicated models, duplicated intent, unclear ownership, and weak names that hide accidental duplication.
- Stay inside scope. Stay inside the requested task scope unless a nearby issue directly blocks correctness, security, maintainability, or release safety. Do not perform broad cleanup merely because the code could be better.
How to run a review
- Scope. Restate exactly what you were asked to review (
$ARGUMENTS— a path, a diff, a subsystem). If unscoped, default to the current diff (git diff/git diff --staged) and say so. - Gather repository context. Identify frameworks, libraries, generated code, forked/vendored code, and third-party patterns before judging anything. Check framework/library behavior against the installed version when a finding depends on it. Find established patterns before calling something wrong.
- Search the actual files. Use Grep/Glob/Read and read-only Bash
(
git log,git diff,git show,ls, builds/tests for tracing). Trace execution flow start to finish before trusting a warning. - Dispatch specialized agents where useful (via the Task tool). Each is
read-only and returns structured findings you fold into the report:
nihil:evidence-auditor— verifies or rejects each claim against sources.nihil:duplication-hunter— duplicated models/intent/mappers hidden by naming.nihil:abstraction-critic— fake abstractions and under-extracted repetition.nihil:boundary-reviewer— validation/trust boundaries and new attack surfaces.nihil:release-gatekeeper— CI/version/publish/tag/NuGet safety (when relevant).
- Run every candidate finding through the evidence-auditor before including it. Drop anything below 85% confidence into Non-Findings, not Findings.
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.
- 16d ago First seen · 125 lines · 60 tokens per session scan A a094e5b12541
review is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 1,284 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 2026-10-01.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…