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 HuntsDesk/ve-kit --skill review-allgit 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-all)<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/review-all"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-all/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/huntsdesk/ve-kit/review-all"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-all.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.01235 |
| Opus 5 | $0.00023 | $0.00617 |
| Sonnet 5 | $0.00009 | $0.00247 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
review-all 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Review Orchestrator
Runs the complete review-* family in sequence and aggregates findings. Use for comprehensive system audits (e.g., post-model-upgrade, quarterly health check, pre-major-initiative sanity check).
Child skills:
/review-agents—.claude/agents/*.md/review-skills—.claude/skills/*/SKILL.md/review-rules—CLAUDE.md+.claude/rules/*.md/review-docs—docs/**/*.md/review-memory—~/.claude/projects/<slug>/memory/*.md/review-board— Vibe Board state (Firestore viamcp__agent-board__*)/review-security—.claude/configuration security posture
Cites ../_shared/review-checklist.md and ../_shared/anthropic-configuration-guide.md.
Owner: docs-manager agent.
When to invoke
- After a Claude model upgrade (e.g., Opus 4.8 → Opus 5)
- After major infrastructure migrations (e.g., Supabase → MIG)
- Quarterly (every ~3 months)
- Before a major initiative where the
.claude/config needs to be trusted
Output contract
A single aggregate report posted to the board + a lean summary to the main agent.
Step 1 — Create audit parent
On the current board project (or create a new "System Audit YYYY-MM-DD" project), create a parent task:
[review-all] System Audit <date>
status: in_progress
priority: high
description: Orchestrated run of review-agents, review-skills, review-rules, review-docs, review-memory.
Capture the parent task ID for all child skills to reference.
Step 2 — Run child skills in sequence
Run in this order (sequential — rules first so deprecated-reference findings surface once centrally, not N times across child reviews):
/review-rules— core instructions are the foundation/review-agents— agents are the most consequential artifacts/review-skills— skills reference agents and rules/review-docs— docs may reference agents, skills, rules/review-memory— memory may reference anything/review-board— Vibe Board hygiene, independent of config layer/review-security— runs last so it sees all flagged references and can cross-check for secrets in files flagged for other reasons
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 · 132 lines · 47 tokens per session scan A 8936b7c82c38
review-all is a skill published in the GitHub repository HuntsDesk/ve-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,235 once invoked, about $0.0002 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
python-debugging
Use this skill when fixing failing Python tests.
repo-scan
Fast orientation for a new codebase.
safe-refactor
Refactor checklist with guardrails.
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.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.