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.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00717 |
| Opus 5 | $0.00034 | $0.00358 |
| Sonnet 5 | $0.00013 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00072 |
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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Fast Review
Contract
| Rule | Detail |
|---|---|
| Trigger | After every delegation — no exceptions |
| Reviewer | Single sub-agent; Economy tier (Standard for premium/security work) |
| Verdict | PASS or FAIL with structured feedback |
| Retry | ≤2 retries on FAIL; 3rd FAIL → panel review |
Procedure
1 — Collect Context
Issue + acceptance criteria, file diff, file partition, deterministic results (lint/test/build), agent self-report.
2 — Spawn Reviewer
One sub-agent, dispatched as the Reviewer. Context = acceptance criteria, diff, partition, deterministic results only — no session history, no delegation prompt.
Agent: Reviewer
Review against these acceptance criteria:
[criteria]
Diff:
[diff]
Deterministic gates: lint ✅ test ✅ build ✅
Full reviewer prompt template: REFERENCE.md.
3 — Parse Verdict
VERDICT: PASS | FAIL
ISSUES:
- [severity:critical|major|minor] Description
FEEDBACK: Actionable feedback.
CONFIDENCE: low | medium | high
- PASS — no critical/major issues (minor noted, non-blocking).
- FAIL — any critical/major issue, or output format mismatch.
Auto-PASS (skip reviewer): pure research/no code changes; docs-only .md changes; ≤10 lines across ≤2 non-sensitive files with all deterministic gates passing.
Sensitive override: Auth/middleware, DB migrations, RLS policies, security headers, CSP, env var schemas, CI/CD config always require review — even 1-line changes.
4 — Handle Verdict
| Outcome | Action |
|---|---|
| PASS | Log review; continue |
| FAIL 1–2 | Log; re-delegate same agent: "Retry N/2 — address listed issues" |
| FAIL 3 | Log escalated: true; load panel-majority-vote skill |
| Panel BLOCK ×3 | Dispute in .opencastle/DISPUTES.md (see team-lead-reference § Dispute Protocol) |
Logging
⛔ HARD GATE — Log the review before proceeding.
npx opencastle log --type review --skill <name> --outcome pass|fail --reviewer "Reviewer" --mechanism sub-agent
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.
- 8d ago First seen · 84 lines · 67 tokens per session scan A 6a1fa069f959
fast-review is a skill published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 717 once invoked, about $0.0003 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 2026-08-30.
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.
code-review
AI-powered code review for diffs and individual files using LLM analysis.
code-review-github
GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge.
code-review-standards
Discover and apply organization coding standards from .forge-review/ configuration.
product-architect
Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…