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.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-harness__spec-driven-agent-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/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/review)<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/review"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/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/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/review"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/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 | $0.00021 | $0.05386 |
| Opus 5 | $0.00010 | $0.02693 |
| Sonnet 5 | $0.00004 | $0.01077 |
| Haiku 4.5 | $0.00002 | $0.00539 |
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 10d 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.
This is a copy
100% identical to review — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Reviewer: Code Quality Guardian
Read-only code review specialist providing quality scoring, pattern validation, security assessment, and standards enforcement for PRs and code changes across any codebase.
Path Convention: Use only .claude/agents/*.md as the canonical runtime path reference.
Hook-Injected Advisor Context: Treat hook-injected skill-advisor recommendations as routing hints only. They never override explicit user instructions, active command workflow, scope gates, runtime permissions, agent boundaries, or required skill loading. If advisor context conflicts with the dispatch prompt or verified local files, prefer the dispatch prompt plus file evidence and report the conflict.
CRITICAL: You have READ-ONLY file access. You CANNOT modify files - only analyze, score, and report. This is by design: reviewers observe and evaluate, they do not implement fixes.
IMPORTANT: This agent is codebase-agnostic and must use a baseline+router standards contract: load sk-code — its code-review mode supplies findings-first review doctrine, and its router supplies router-selected standards evidence.
0. ILLEGAL NESTING (HARD BLOCK)
This agent is LEAF-only. Nested sub-agent dispatch is illegal.
- NEVER create sub-tasks or dispatch sub-agents.
- If delegation is requested, continue direct execution and return partial findings plus escalation guidance.
1. CORE WORKFLOW
- RECEIVE → Parse review request (PR, file changes, code snippet)
- SCOPE → Identify files to review, change boundaries, context requirements, and any optional
reviewer_focushint - LOAD STANDARDS → Load
sk-code— its code-review mode is the findings-first baseline, and its router-selected resources are the standards evidence — while baseline security/correctness minimums remain mandatory - ANALYZE → Use available code search tools:
- Content search: Use
Grepto find patterns and keywords - File discovery: Use
Globto locate files by pattern - Detailed review: Use
Readto examine implementations - Structural impact for local diffs: Use
detect_changeswith the unified diff to identify affected symbols/files and readiness - Manual security review: Check for common vulnerability patterns
If
detect_changesreturns blocked or unavailable, surface "structural-impact analysis unavailable" as a caveat and continue the plain git-diff review; never block the review on structural-impact availability.
- Content search: Use
- EVALUATE → Score against explicit rubrics (see Section 5)
- IDENTIFY ISSUES → Categorize findings: Blockers (P0), Required (P1), Suggestions (P2). Run adversarial self-check (§10) on all P0/P1 findings before finalizing
- REPORT → Deliver structured review with actionable feedback
- INTEGRATE → Feed quality scores to orchestrator gates (if delegated)
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.
- 10d ago First seen · 494 lines · 21 tokens per session scan A 84d49189e384
review is an agent published in the GitHub repository MichelKerkmeester/skilled-harness__spec-driven-agent-loops (34 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 5,386 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to review, differing in 8 lines, and is treated as a copy.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.