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 agentmods add skills/huntsdesk/ve-kit/review-rulesnpx skills add HuntsDesk/ve-kit --skill review-rulesgit clone --depth 1 https://github.com/HuntsDesk/ve-kitWrote 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/huntsdesk/ve-kit/review-rules)<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/review-rules"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-rules.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01274 |
| Opus 5 | $0.00028 | $0.00637 |
| Sonnet 5 | $0.00011 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
review-rules 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 6d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules & Core Instructions Review Protocol
Reviews the always-loaded instruction layer that governs every Claude Code session in this repo. Scope:
CLAUDE.md(project root).claude/rules/*.md.claude/settings.jsonhooks config (only to verify rule-hook alignment)
Part of the review-* skill family. Cites ../_shared/review-checklist.md and ../_shared/anthropic-configuration-guide.md.
Owner: docs-manager agent.
When to invoke
- CLAUDE.md approaching 150 lines (lean limit) or > 200 lines
- After significant process changes (new hooks, new RIPER modes, new deployment patterns)
- Quarterly audit
- When new team members or agents repeatedly make mistakes the rules should prevent
Output contract
Board tasks only. Lean summary to main agent.
Step 1 — Inventory
- Read
CLAUDE.md. Record line count, section list, referenced rules/skills/docs/agents. - Read every
.claude/rules/*.md. Record line count, topic, referenced files. - Read
.claude/settings.jsonhooks block. Record which hooks exist and what they enforce.
Step 2 — Size discipline
| Artifact | Target | Hard limit |
|---|---|---|
| CLAUDE.md | < 150 lines | 200 lines |
| Individual rule | < 200 lines | 300 lines |
Flag bloat. Recommend:
- CLAUDE.md bloat → push detail into a new rule or existing rule
- Rule bloat → split by sub-topic or move deep reference to a skill / doc
Step 3 — Staleness
For each rule and for CLAUDE.md, check:
- Deprecated infrastructure references (Supabase Edge Functions, old table names, retired services)
- Domain names and URLs still current ( variants, MIG host IDs, LB IP
<YOUR_LB_IP>) - Model IDs match current Anthropic lineup (Opus 5, Fable 5, Sonnet 5, Haiku 4.5)
- Command references valid (
Enter C -push-dev,Enter C -push,Enter C -all) - Stripe API version current (
2026-04-22.dahliaper CLAUDE.md) - Referenced docs exist (every
[link](path)resolves) - Referenced agents exist in
.claude/agents/ - Referenced skills exist in
.claude/skills/
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.
- 6d ago First seen · 132 lines · 57 tokens per session scan A 9fa65d754ec4
review-rules is a skill published in the GitHub repository HuntsDesk/ve-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,274 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 2026-08-31.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.