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 jdutton/vibe-agent-toolkit --skill skillsgit clone --depth 1 https://github.com/jdutton/vibe-agent-toolkitWrote 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/jdutton/vibe-agent-toolkit/skills)<a href="https://agentmods.dev/skills/jdutton/vibe-agent-toolkit/skills"><img src="https://agentmods.dev/badge/skills/jdutton/vibe-agent-toolkit/skills/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/jdutton/vibe-agent-toolkit/skills"><img src="https://agentmods.dev/badge/skills/jdutton/vibe-agent-toolkit/skills.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 | $0.00054 | $0.01111 |
| Opus 5.5 | $0.00022 | $0.00444 |
| Sonnet 5.5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
vibe-agent-toolkit 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Agent Toolkit
Vibe Agent Toolkit (VAT) is a modular toolkit for building, packaging, and distributing portable AI agents and skills that work across multiple Claude surfaces and adjacent frameworks. Write skill or agent content once; VAT handles validation, packaging, plugin/marketplace layout, and npm publishing.
This is a router skill. Load the sibling sub-skill that matches the work you're doing — each sub-skill owns one slice of VAT's surface and is designed to be pulled in on demand.
When to Use VAT
Good fits:
- Publishing a Claude skill or plugin to npm with a proper marketplace layout
- Multi-runtime agent projects (Vercel AI SDK, LangChain, OpenAI, Claude Agent SDK)
- Validating plugins / skills / marketplaces with
vat auditbefore shipping - Enforcing frontmatter schemas across large markdown corpora
- Wiring RAG indexing into an agent project
Poor fits:
- Simple one-off scripts where the framework is already decided
- Non-TypeScript/JavaScript projects
- Cases where you need deep framework-specific features with no reuse goal
Picking a Sub-skill
| If you're working on... | Load |
|---|---|
New project setup, vibe-agent-toolkit.config.yaml orientation, repo structure, vibe-validate integration, npm postinstall |
vibe-agent-toolkit:vat-adoption-and-configuration |
| Writing or revising a SKILL.md — frontmatter, body, references, packagingOptions, validation overrides | vibe-agent-toolkit:vat-skill-authoring |
TypeScript agent archetypes, agent.yaml, result envelopes, orchestration, runtime adapters |
vibe-agent-toolkit:vat-agent-authoring |
vat audit on plugins, marketplaces, skills, or settings — including --compat, --exclude, --user, CI use |
vibe-agent-toolkit:vat-audit |
Markdown collections, resources: config, frontmatter schema validation, vat resources validate |
vibe-agent-toolkit:vat-knowledge-resources |
Asking the resource projection SQL questions (vat resources query) or declaring standing SQL assertions that gate CI (vat resources check, --budget) |
vibe-agent-toolkit:vat-knowledge-resources |
vat build, vat verify, plugin/marketplace layout, npm publishing, postinstall |
vibe-agent-toolkit:vat-skill-distribution |
vat rag index / vat rag query, installing the opt-in RAG backends, embedding providers, vector stores, chunking |
vibe-agent-toolkit:vat-rag |
Pre-publication quality review, vat skill review, validation-code triage |
vibe-agent-toolkit:vat-skill-review |
Behaviorally testing a packaged skill in isolation — vat skill test run/configure, friction triage, auth modes, security caveats |
vibe-agent-toolkit:vat-skill-testing |
Anthropic Admin API: org users, cost/usage, workspace skills, ANTHROPIC_ADMIN_API_KEY |
vibe-agent-toolkit:vat-enterprise-org |
| Programmatic markdown/frontmatter edits — moving files, updating references, schema-evolution migrations; comment-preserving FrontmatterEditor + rewriteBodyLinks | vibe-agent-toolkit:markdown-rewriting |
| Auditing a codebase for COHERENCE rather than bugs — does every lane implement one contract, does a status tell the truth, is a passing test suite blind | vibe-agent-toolkit:coherence-audit |
What ships with it
48 files 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.
- CLAUDE.md 9.4 KB
- coherence-audit.md 8.3 KB
- evals/coherence-audit/evals.json 8.4 KB
- evals/coherence-audit/fixtures/status-collapse/reporter.test.ts 1.4 KB runs code
- evals/coherence-audit/fixtures/status-collapse/reporter.ts 1.6 KB runs code
- evals/coherence-audit/fixtures/vendor-claim/install-paths.ts 839 B runs code
- evals/markdown-rewriting/evals.json 9.9 KB
- evals/markdown-rewriting/fixtures/docs/specs/auth-spec.md 840 B
- evals/markdown-rewriting/fixtures/docs/specs/billing-spec.md 436 B
- evals/markdown-rewriting/fixtures/schemas/spec.schema.json 464 B
- evals/vat-agent-authoring/evals.json 9.9 KB
- evals/vat-agent-authoring/fixtures/sequential-pipeline.ts 608 B runs code
- evals/vat-agent-authoring/fixtures/throwing-analyzer.ts 1.2 KB runs code
- evals/vat-audit/evals.json 7.7 KB
- evals/vat-audit/fixtures/claims-toolkit-plugin/.claude-plugin/plugin.json 266 B
- evals/vat-audit/fixtures/claims-toolkit-plugin/skills/loss-run-parser/SKILL.md 682 B
- evals/vat-audit/fixtures/expense-categorizer-plugin/.claude-plugin/plugin.json 207 B
- evals/vat-audit/fixtures/expense-categorizer-plugin/skills/categorizing-expenses/references/gl-codes.md 211 B
- evals/vat-audit/fixtures/expense-categorizer-plugin/skills/categorizing-expenses/SKILL.md 711 B
- evals/vat-audit/fixtures/release-notifier-plugin/.claude-plugin/plugin.json 188 B
- evals/vat-audit/fixtures/release-notifier-plugin/skills/release-announce/scripts/notify.py 1.5 KB runs code
- evals/vat-audit/fixtures/release-notifier-plugin/skills/release-announce/SKILL.md 610 B
- evals/vat-knowledge-resources/evals.json 9.0 KB
- evals/vat-knowledge-resources/fixtures/broken-collections-config.yaml 335 B
- evals/vat-knowledge-resources/fixtures/sample-adr-frontmatter.md 322 B
- evals/vat-knowledge-resources/fixtures/sample-system-frontmatter.md 251 B
- evals/vat-knowledge-resources/fixtures/starter-config.yaml 99 B
- evals/vat-rag/evals.json 8.1 KB
- evals/vat-skill-authoring/evals.json 10 KB
- evals/vat-skill-authoring/fixtures/misplaced-config-skill.md 787 B
- evals/vat-skill-distribution/evals.json 11 KB
- evals/vat-skill-distribution/fixtures/package-devdep.json 645 B
- evals/vat-skill-distribution/fixtures/package-missing-dist.json 526 B
- evals/vat-skill-review/evals.json 6.6 KB
- evals/vat-skill-review/fixtures/bad-frontmatter-skill.md 639 B
- evals/vat-skill-review/fixtures/clean-skill.md 844 B
- evals/vat-skill-review/fixtures/nonportable-cli-skill.md 647 B
- markdown-rewriting.md 9.9 KB
- vat-adoption-and-configuration.md 12 KB
- vat-agent-authoring.md 8.5 KB
- vat-audit.md 10 KB
- vat-enterprise-org.md 14 KB
- vat-knowledge-resources.md 27 KB
- vat-rag.md 7.3 KB
- vat-skill-authoring.md 26 KB
- vat-skill-distribution.md 24 KB
- vat-skill-review.md 21 KB
- vat-skill-testing.md 52 KB
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.
- 1mo ago Changed · +57 lines · +38 tokens per session f6890a6982e4
- 2mo ago First seen · 13 lines · 16 tokens per session scan A 626f456315b8
vibe-agent-toolkit is a skill published in the GitHub repository jdutton/vibe-agent-toolkit (2 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,111 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.