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 sangrokjung/claude-forge --skill review-loopgit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/sangrokjung/claude-forge/review-loop)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/review-loop"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/review-loop/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/sangrokjung/claude-forge/review-loop"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/review-loop.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 | $0.00100 | $0.01314 |
| Opus 5 | $0.00050 | $0.00657 |
| Sonnet 5 | $0.00020 | $0.00263 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
review-loop 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-loop — the independent adversarial loop
Nobody grades their own exam. The maker implements, a separate fresh checker tries to break the claim, and the two alternate until the checker approves the code as it stands right now.
When this applies
Any change to behaviour: executable code, shell/Python/JS/TS/SQL, CI/CD, hooks, commands, agent and skill definitions, runtime prompts, and configuration that changes what the system does.
Exempt: prose documentation, marketing copy, typos, and formatting that cannot change behaviour. When a documentation-only change also touches something a runtime reads, it is behavioural. If you are unsure which side a change falls on, treat it as behavioural.
File count and diff size are not exemptions. A one-line change to an authorization check is behavioural; a 900-line documentation reflow is not.
| Risk | Lanes required |
|---|---|
| Ordinary behavioural change | 1 independent checker |
| Auth, authorization, payments, access-control rules, secrets, destructive data changes, irreversible deploys | 2 lanes, run by different checkers: correctness plus the risk-specific angle (runtime security, or rollback) |
The loop
maker implements → targeted test / real-surface QA → fresh checker
↑ │
└────────── REQUEST_CHANGES ← findings ──────────────┘
│
APPROVE on current code → done
There are exactly three verdicts: APPROVE, REQUEST_CHANGES, UNVERIFIED.
- APPROVE is a completion candidate only when it was issued against the revision that is checked out now, with evidence produced from that same revision.
- REQUEST_CHANGES means the maker fixes the findings surgically, re-runs the tests, and calls a fresh checker again. Fixing more than the findings restarts the argument.
- UNVERIFIED means no judgement was reached: the checker never ran, returned empty, timed out, errored, was rate-limited, returned a malformed envelope, or reviewed a state that has since moved. It is not a pass. Retry with a different checker, runtime, or strategy.
What ships with it
1 file 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.
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.
- 5d ago First seen · 112 lines · 100 tokens per session scan A a8752b46e0a0
review-loop is a skill published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed 5d ago), licensed MIT. It adds 100 tokens to every session and 1,314 once invoked, about $0.0005 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
log-analyzer
Senior-SRE log analysis specialist. Use when investigating incidents from logs, triaging error spikes, extracting timelines, correlating distributed traces, or separating signal from noise across plain-text, JSON (slog/zap), syslog, journald, container, and Kubernetes logs. ALWAYS use when the user asks to "analyze…
go-code-reviewer
Review Go code with a defect-first approach using repository policy (constitution.md first, then AGENTS.md fallback). Use for code review, PR review, quality checks, risk analysis, and regression detection.
go-review-lead
Orchestrate a comprehensive Go code review by triaging code changes, dispatching vertical review skills (security, concurrency, error, logic, performance, quality, test, observability) as parallel agents, then consolidating results into a unified report. Use for full Go PR review or comprehensive code review. Replaces…
incident-postmortem
Incident post-mortem specialist for writing blameless post-mortems, extracting timelines from logs/events, conducting root cause analysis (5-Why, fishbone), classifying severity, and generating tracked action items. ALWAYS use when writing a post-mortem, reviewing an incident, extracting a timeline, performing root…
security-review
A code-security review guide that checks code changes, pull requests, or services for risks an attacker could exploit.
systematic-debugging
Use when debugging, diagnosing, or investigating any bug, test failure, flaky test, race condition, unexpected behavior, build failure, production incident, third-party breakage, root cause analysis, or performance regression before proposing fixes.