Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HuntsDesk/ve-kitnpx agentmods add skills/huntsdesk/ve-kit/review-agentsWrote 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-agents)<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/review-agents"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-agents.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 | $0.01688 |
| Opus 5 | $0.00028 | $0.00844 |
| Sonnet 5 | $0.00011 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
review-agents 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Review Protocol
Comprehensive review of every .claude/agents/*.md file. Part of the review-* skill family. Cites ../_shared/review-checklist.md and ../_shared/anthropic-configuration-guide.md.
Owner: docs-manager agent.
When to invoke
- Periodic audit (quarterly or after major infrastructure changes)
- After model upgrades (e.g., Opus 4.8 → Opus 5)
- When new services, features, or domains land without a specialist
- Before a big delegation-heavy initiative where agent accuracy matters
Output contract
This skill produces only board tasks. It does not write findings into the conversation. Main-agent output = a lean summary pointing to the Vibe Board parent task.
Step 1 — Inventory
Read every file matching .claude/agents/*.md. Extract:
name,description,model,color,memory,tools(if present)- Trigger keywords from description
- File/path references (via regex for
.md,src/,services/,docs/) - Service references (cross-check with
services/directory) - Table references (cross-check with Postgres schema)
- Code snippets (language fence blocks)
<example>block count
Record in a structured list. Don't dump it to the user.
Step 2 — Frontmatter validation
Apply the schema from review-checklist.md §"Agents". For each agent, flag:
| Issue | Severity |
|---|---|
Missing name or mismatched with filename |
critical |
Missing description |
critical |
Missing model (defaulting to inherit without justification) |
high |
description uses undocumented frontmatter conventions |
medium |
No <example> blocks or only 1 |
medium |
No <commentary> in examples |
low |
description + when_to_use combined > 1,536 chars |
high |
| Uses invented (non-Anthropic) keys | high |
Step 3 — Description quality
Check each description against the canonical pattern:
[role]. [what it does]. [when to invoke + triggers].
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 · 176 lines · 57 tokens per session scan A e06db5f24943
review-agents 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 1,688 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
safe-refactor
Refactor checklist with guardrails.
pr-triage
First-touch triage for external pull requests - verdict, label, and a welcoming comment within minutes of open.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
[REPLACE: SKILL_NAME]
First-touch review of newly opened PRs on [REPLACE: WATCHEDREPO] — verdict + welcoming comment + label.
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…