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 monkilabs/opencastle --skill fast-reviewgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/fast-review)<a href="https://agentmods.dev/skills/monkilabs/opencastle/fast-review"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/fast-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/monkilabs/opencastle/fast-review"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/fast-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Data Exfiltration · line 20 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium MCP Rug Pull · line 70 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00042 | $0.00540 |
| Opus 5.5 | $0.00017 | $0.00216 |
| Sonnet 5.5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
fast-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 18d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast Review
A change is reviewed by someone who did not write it: one reviewer — a sub-agent dispatched as the Reviewer — who sees only what it needs.
When to skip it
No reviewer for research with no code change, a docs-only change, or ≤10 lines across ≤2 files with the project's tests, lint and build passing — except auth or middleware, migrations, access policies, security headers or CSP, environment variable schemas, and CI/CD config, which are reviewed even for one line. A review never replaces tests, lint and build: run those first.
Review
Give the reviewer the acceptance criteria, the diff, the files the change was allowed to touch, and the results of the tests, lint and build — not the conversation or the delegation prompt: it judges the result, not the intent.
You review a change. Be concise and specific.
Task: <title>. Acceptance criteria: <list>
Files it may change: <paths>
Diff: <diff>
Tests / lint / build: <passed or failed>
Previous FAIL, on a retry: <its feedback>
Check: the criteria are met · only the allowed files changed · nothing regressed ·
errors are surfaced, not swallowed · the types are sound · no secret or injection
vector · the edge cases are handled.
VERDICT: PASS | FAIL
ISSUES:
- [critical|major|minor] <description, file:line>
FEEDBACK: <what to change>
PASS: no critical or major issue; minor ones are noted, not blocking. FAIL: any critical or major issue, or an answer not in that shape.
After a FAIL
| What happened | What to do |
|---|---|
| FAIL, the first or second time | Fix it, or send it back to its author with the feedback ("retry N of 2"), and review again |
| FAIL a third time | A panel of three (panel-majority-vote) |
| The panel blocks it, or the reviewers disagree on what is right | Stop, and tell the user what blocks it, with each side's evidence |
| The agent crashes, times out or returns nothing usable, twice | Stop and tell the user; do not try a third time |
A panel costs three reviews: it is not a fast review. Never accept a FAIL without fixing it or asking.
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.
- 18d ago Changed · -37 lines · +6 tokens per session 63cb2dbf0c2b
- 20d ago Changed · -31 tokens per session 7ed6c84deb9c
- 21d ago Changed · +2 lines cbcea2dc8818
- 1mo ago First seen · 84 lines · 67 tokens per session scan A 6a1fa069f959
fast-review is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 540 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 2026-08-30.
Other skills, from other repositories
simplify-skill
Universal, high-intelligence ecosystem-aware code simplification skill. Detects ANY programming language, framework, package manager, and exact version in use. Consults modern documentation via web search and Context7, and orchestrates specialized sub-agents applying strict, universal engineering heuristics.
code-review
Use when code has been written and needs validation before committing, or when the user asks for a code review or security check.
gentle-ai-judgment-day
Trigger: judgment day, judgement day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
code-reviewer
Staff-engineer-level code review delivering 10 prioritized actionable findings across architecture, security, performance, and maintainability.