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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-code-reviewgit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-review)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-review"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-review"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-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 | $0.00029 | $0.06243 |
| Opus 5 | $0.00015 | $0.03121 |
| Sonnet 5 | $0.00006 | $0.01249 |
| Haiku 4.5 | $0.00003 | $0.00624 |
Grade A, and why
sk-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 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.
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 — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review Mode - Stack-Agnostic Findings-First Review
Universal findings-first review baseline paired with sk-code surface standards evidence for the detected code surface.
1. WHEN TO USE
Activation Triggers
Use the code-review mode (of the sk-code family) when:
- A user asks for code review, PR review, quality gate, or merge readiness.
- A workflow dispatches
@reviewfor pre-commit or gate validation. - A user requests security/correctness risk analysis before merge.
- A user wants severity-ranked findings with file:line evidence.
Keyword Triggers
review, code review, pr review, audit, security review, quality gate, request changes, findings, blocking issues, merge readiness
Use Cases
- Review-only pass: findings-first output with no code edits.
- Gate validation: score + pass/fail recommendation for orchestrated workflows.
- Focused risk pass: security, concurrency, correctness, or removal-focused review.
When NOT to Use
- Feature implementation without review intent; use the surface skill (
code-webflow/code-opencode). - Pure documentation editing where code behavior is not being assessed.
- Git-only workflow tasks (branching, rebasing, commit hygiene) without code-quality evaluation intent.
- Applying review fixes after findings are accepted; use the surface skill (
code-webflow/code-opencode). - Author-side quality gates before review; use
code-quality. - Root-cause debugging; use the surface's
workflow-debug.mddoctrine. - Verification evidence collection; use the surface's
workflow-verify.mddoctrine.
2. SMART ROUTING
Primary Detection Signal
Review behavior follows a baseline+surface-evidence model:
- Baseline (always): the
code-reviewmode (of the sk-code family) findings-first doctrine. - Surface standards evidence (when available):
sk-codedetected surface resources. - Unknown surfaces: review against baseline security/correctness only and disclose uncertainty.
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.
- assets/code-quality-checklist.md 7.1 KB
- assets/fix-completeness-checklist.md 4.0 KB
- assets/removal-plan.md 3.4 KB
- assets/security-checklist.md 5.9 KB
- assets/solid-checklist.md 4.1 KB
- assets/test-quality-checklist.md 5.8 KB
- benchmark/reports/2026-07-10--live-mode-b--live/failed-runs.md 186 B
- benchmark/reports/2026-07-10--live-mode-b--live/findings-and-recommendations.md 234 B
- benchmark/reports/2026-07-10--live-mode-b--live/README.md 1.4 KB
- benchmark/reports/2026-07-10--live-mode-b--live/results.csv 472 B
- benchmark/reports/2026-07-10--live-mode-b--live/skill-benchmark-report.json 25 KB
- benchmark/reports/2026-07-10--live-mode-b--live/skill-benchmark-report.md 1.8 KB
- benchmark/reports/2026-07-10--live-mode-b--live/source.md 906 B
- benchmark/reports/2026-07-10--router-mode-a--router/failed-runs.md 188 B
- benchmark/reports/2026-07-10--router-mode-a--router/findings-and-recommendations.md 236 B
- benchmark/reports/2026-07-10--router-mode-a--router/README.md 1.4 KB
- benchmark/reports/2026-07-10--router-mode-a--router/results.csv 500 B
- benchmark/reports/2026-07-10--router-mode-a--router/skill-benchmark-report.json 24 KB
- benchmark/reports/2026-07-10--router-mode-a--router/skill-benchmark-report.md 2.4 KB
- benchmark/reports/2026-07-10--router-mode-a--router/source.md 917 B
- benchmark/reports/README.md 1.5 KB
- changelog/v1.0.0.0.md 2.1 KB
- changelog/v1.1.0.0.md 1.4 KB
- changelog/v1.2.0.0.md 1.0 KB
- changelog/v1.3.0.0.md 6.5 KB
- changelog/v1.4.0.0.md 6.7 KB
- changelog/v1.5.0.0.md 4.0 KB
- changelog/v1.6.0.0.md 2.0 KB
- manual-testing-playbook/baseline-review-flow/large-refactor-pr.md 4.8 KB
- manual-testing-playbook/baseline-review-flow/multi-commit-feature-branch.md 4.8 KB
- manual-testing-playbook/baseline-review-flow/small-pr-single-file.md 4.5 KB
- manual-testing-playbook/cross-cli-orchestration/cli-opencode-and-cli-claude-code-handback.md 5.4 KB
- manual-testing-playbook/cross-cli-orchestration/cli-opencode-delegation.md 5.1 KB
- manual-testing-playbook/cross-cli-orchestration/native-claude-code-invocation.md 5.0 KB
- manual-testing-playbook/efficiency-and-restraint/ceiling-comment-downgrade.md 6.0 KB
- manual-testing-playbook/efficiency-and-restraint/reinvent-the-wheel-detection.md 5.4 KB
- manual-testing-playbook/efficiency-and-restraint/review-depth-alias.md 6.2 KB
- manual-testing-playbook/efficiency-and-restraint/rule-invariant-canary.md 5.7 KB
- manual-testing-playbook/efficiency-and-restraint/unrequested-code-removal.md 5.6 KB
- manual-testing-playbook/intra-routing-recall/dry.md 5.2 KB
- manual-testing-playbook/intra-routing-recall/kiss.md 5.3 KB
- manual-testing-playbook/intra-routing-recall/quality.md 5.4 KB
- manual-testing-playbook/intra-routing-recall/removal.md 5.3 KB
- manual-testing-playbook/intra-routing-recall/security.md 5.3 KB
- manual-testing-playbook/intra-routing-recall/solid.md 5.6 KB
- manual-testing-playbook/intra-routing-recall/testing.md 5.4 KB
- manual-testing-playbook/manual-testing-playbook.md 37 KB
- manual-testing-playbook/re-review-and-stale-context/ai-generated-code-suspect-quality.md 5.0 KB
- manual-testing-playbook/re-review-and-stale-context/re-review-after-fixes.md 4.7 KB
- manual-testing-playbook/re-review-and-stale-context/stale-architecture-fresh-pass.md 4.8 KB
- manual-testing-playbook/scope-and-precedence/baseline-vs-surface-precedence.md 4.9 KB
- manual-testing-playbook/scope-and-precedence/explicit-scope-security-only.md 4.9 KB
- manual-testing-playbook/scope-and-precedence/test-code-review.md 4.6 KB
- manual-testing-playbook/security-and-correctness-minimums/input-validation-injection.md 4.8 KB
- manual-testing-playbook/security-and-correctness-minimums/secrets-and-hardcoded-creds.md 4.8 KB
- manual-testing-playbook/security-and-correctness-minimums/security-sensitive-auth.md 4.8 KB
- manual-testing-playbook/severity-and-evidence-discipline/class-of-bug-vs-instance-only.md 4.9 KB
- manual-testing-playbook/severity-and-evidence-discipline/cross-consumer-affected-surface.md 4.9 KB
- manual-testing-playbook/severity-and-evidence-discipline/p0-blocker-with-file-line.md 4.6 KB
- manual-testing-playbook/structural-impact-preflight/detect-changes-assisted-review.md 5.8 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 12a24a3c9669
- 7d ago First seen · 545 lines · 29 tokens per session scan A ea139a92bef6
sk-code-review is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 6,243 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.