Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ncoevoet/claude-review-allnpx agentmods add skills/ncoevoet/claude-review-all/review-allWrote 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/ncoevoet/claude-review-all/review-all)<a href="https://agentmods.dev/skills/ncoevoet/claude-review-all/review-all"><img src="https://agentmods.dev/badge/skills/ncoevoet/claude-review-all/review-all/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/ncoevoet/claude-review-all/review-all"><img src="https://agentmods.dev/badge/skills/ncoevoet/claude-review-all/review-all.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 314 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Excessive Agency · line 301 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 6 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 164 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 475 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00074 | $0.11890 |
| Opus 5 | $0.00037 | $0.05945 |
| Sonnet 5 | $0.00015 | $0.02378 |
| Haiku 4.5 | $0.00007 | $0.01189 |
Grade A, and why
review-all scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Claude Code only.** This skill orchestrates git, gh, lsof/ss, curl, jq, and shell scripts via Bash, and relies on filesystem access for sibling reference reads. Not portable to claude.ai uploads or the Claude API runti How it starts
The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive Code Review Orchestrator
Surface
Claude Code only. This skill orchestrates git, gh, lsof/ss, curl, jq, and shell scripts via Bash, and relies on filesystem access for sibling reference reads. Not portable to claude.ai uploads or the Claude API runtime (no network access, no shell, no on-disk skill tree). The allowed-tools frontmatter field is honored by Claude Code as a slash-command convention; on other surfaces it has no effect.
Prerequisites: agent personas live alongside this file at agents/ and phase reference docs at references/. The installer (make install, which runs rsync per the repo Makefile) copies the entire skills/review-all/ directory to ~/.claude/skills/review-all/, so the relative layout is identical in-repo and installed: this file Reads agents/<id>.md and references/<name>.md by sibling path at runtime.
You are a comprehensive, project-agnostic code review orchestrator. You combine simplification analysis, code quality/smell detection, deterministic toolchain gates, and deep heuristic review into a single unified local review. Launch teams of parallel agents for speed and coverage, then verify every finding independently before reporting.
Review target: $ARGUMENTS
Core principles:
- Cover everything — never miss a real issue
- Verify everything — never report a false positive
- Evidence-based — every finding must cite file:line and show proof
- Project-agnostic — discover conventions from the repo, never assume them
- When uncertain, assume the developer knows something you don't
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/_shared.md 12 KB
- agents/01-standards.md 1.4 KB
- agents/02-bugs-security.md 6.5 KB
- agents/03-dry-smells.md 2.5 KB
- agents/04-consistency-history.md 1.6 KB
- agents/05-simplification.md 1.5 KB
- agents/06-security-deep-dive.md 4.4 KB
- agents/07-performance.md 3.8 KB
- agents/08-test-quality.md 2.5 KB
- agents/09-api-contract.md 3.0 KB
- agents/10-a11y-i18n.md 2.8 KB
- agents/verifier.md 13 KB
- evals/01-small-diff-null-deref.json 1.6 KB
- evals/02-large-refactor-no-noise.json 1.5 KB
- evals/03-auth-crypto-change.json 1.6 KB
- evals/04-empty-diff-noop.json 992 B
- evals/05-false-positive-resistance.json 2.2 KB
- evals/06-preexisting-vuln-in-audit.json 1.9 KB
- evals/07-dry-duplication.json 1.4 KB
- evals/08-n-plus-one.json 1.4 KB
- evals/09-missing-test-gate.json 1.7 KB
- evals/10-api-contract-break.json 1.8 KB
- evals/11-a11y-missing-label.json 1.3 KB
- evals/12-i18n-hardcoded-string.json 1.4 KB
- evals/13-race-lost-update.json 1.5 KB
- evals/14-resource-leak.json 1.4 KB
- evals/15-deleted-file-breaks-importer.json 1.4 KB
- evals/16-unit-mismatch-seconds-ms.json 2.1 KB
- evals/17-unguarded-request-body.json 2.0 KB
- evals/18-swallowed-exception.json 1.9 KB
- evals/19-generated-file-noise-floor.json 3.1 KB
- evals/20-cache-invalidation-storm.json 1.9 KB
- evals/21-subscription-leak.json 2.0 KB
- evals/22-cache-on-failure.json 2.1 KB
- evals/23-missing-await-floating-promise.json 1.9 KB
- evals/24-off-by-one-pagination.json 1.6 KB
- evals/25-inverted-access-guard.json 1.7 KB
- evals/26-uninitialized-field.json 1.9 KB
- evals/27-path-traversal.json 1.8 KB
- evals/28-secret-in-log.json 1.6 KB
- evals/29-memoize-key-collision.json 2.0 KB
- evals/30-switch-missing-case.json 1.9 KB
- evals/31-xss-innerhtml.json 1.5 KB
- evals/32-open-redirect.json 1.6 KB
- evals/33-unbounded-cache-growth.json 2.0 KB
- evals/34-command-injection.json 1.6 KB
- evals/35-regex-redos.json 1.8 KB
- evals/36-insecure-randomness.json 1.5 KB
- evals/37-ssrf.json 1.7 KB
- evals/38-tls-verification-disabled.json 1.5 KB
- evals/39-integer-precision-loss.json 1.6 KB
- evals/40-missing-query-limit.json 1.6 KB
- evals/41-async-foreach.json 1.8 KB
- evals/42-concurrent-modification.json 1.6 KB
- evals/43-jdbc-resource-leak.json 1.9 KB
- evals/44-blank-secret-auth-bypass.json 1.7 KB
- evals/45-non-thread-safe-map.json 1.9 KB
- evals/46-broken-double-checked-locking.json 1.8 KB
- evals/47-io-under-lock.json 2.1 KB
- evals/48-swallowed-interrupt.json 2.0 KB
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.
- today Changed · +4 lines 743771bc50c1
- 8d ago Changed · +30 lines b26961879d97
- 12d ago First seen · 478 lines · 74 tokens per session scan A 0efc789a31f6
review-all is a skill published in the GitHub repository ncoevoet/claude-review-all (28 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 11,890 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Failure Modes & Observability in Design
Ensure designs specify failure modes, timeouts, error contracts, and observability for critical flows.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
aesthetic-instrument
A committed aesthetic in the sense of skills/committed-aesthetic/SKILL.md: every rule below is checkable, and every value was read out of the source — packages/board/public/index.html and greatcto-site/styles.css — rather than chosen to write this document.
committed-aesthetic
How to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an agent pick, and it picks the modal option; a committed aesthetic makes it execute one thing precisely, against rules you can check. Use when a design keeps coming out competent and forgettable, when…
observability-baseline
Scaffold-time observability so a shipped product is not blind in prod from day one — error capture (Sentry), request-id structured logging, and /healthz + /readyz endpoints. stack-baseline pins Sentry but nothing wires it; this is the wiring. Loaded by app-scaffolder (bake into the scaffold), infra-provisioner (prod…