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 autoworks-ai/autovault --skill skill-authorgit clone --depth 1 https://github.com/autoworks-ai/autovaultWrote 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/autoworks-ai/autovault/skill-author)<a href="https://agentmods.dev/skills/autoworks-ai/autovault/skill-author"><img src="https://agentmods.dev/badge/skills/autoworks-ai/autovault/skill-author/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/autoworks-ai/autovault/skill-author"><img src="https://agentmods.dev/badge/skills/autoworks-ai/autovault/skill-author.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 | $0.00028 | $0.01473 |
| Opus 5 | $0.00014 | $0.00737 |
| Sonnet 5 | $0.00006 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
skill-author 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 9d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoVault Skill Packager
Prepare an existing SKILL.md or skill directory for AutoVault admission. This
skill is about AutoVault packaging: schema correctness, bundle membership,
capability declarations, validation, deduplication, and signed installation.
Scope
Use this skill when:
- a workflow or draft already exists and needs valid AutoVault frontmatter;
- a bundle has support files that must be inventoried and declared;
- an AutoVault validation, security, or dedup result needs remediation; or
- a reviewed bundle is ready for
propose_skilloradd_skill.
Do not use it for open-ended workflow invention, trigger design, or general
skill-writing pedagogy. Use the host-native skill-creator or equivalent design
tool first, then return here once there is a concrete draft to package.
1. Check for an existing capability
If the AutoVault compatibility tools are connected, search with
get_skill({query: "specific workflow nouns"}). Prefer extending or reusing a
good match over adding another near-duplicate.
When the MCP tools are absent, inspect the host's normal visible skill directory instead. AutoVault-managed skills are synced into those native directories, so filesystem discovery is sufficient and the missing MCP server is not an error.
2. Inventory the complete bundle
Treat the skill directory as one unit:
SKILL.mdis the entry point.- Every regular sibling file under the directory is a resource.
- Exclude OS/editor metadata and generated caches.
- Reject symlinks, path traversal, device files, and other non-regular entries.
- Review executable resources as carefully as the skill body.
For a GitHub source, AutoVault fetches all regular sibling files beneath the
selected skill directory at one immutable commit. It does not rely on the
upstream author having declared every file. Missing resources declarations
are synthesized during normalization, and the install response reports
inferred_resources for review.
3. Normalize frontmatter
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.
- 9d ago First seen · 188 lines · 28 tokens per session scan A dcf0c9cdc33c
skill-author is a skill published in the GitHub repository autoworks-ai/autovault (3 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 1,473 once invoked, about $0.0001 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
js-gof
Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…
error-handling
Apply error handling and recovery patterns in JavaScript/TypeScript or Node.js. Use when implementing error handling, retry logic, or when the user mentions domain errors, error recovery, error escalation.
js-conventions
Apply Metarhia JavaScript style. Use when writing or editing .js, .mjs, .ts files (with certain corrections for typescript), formatting code, or when the user asks about code style or linting.
pn-best-of-n
Run 2–3 competing implementations of the same spec in isolated worktrees, eliminate failures via objective gates, then judge survivors with a separate premium-tier pass. Use for ambiguous algorithm/API/refactor choices with strong tests — not auth/security paths.
pn-deprecation-and-removal
Sunsetting APIs, features, and dead code — deprecation levels, migration windows, Hyrum's Law, zombie code removal. Use when removing or replacing user-visible behavior, public APIs, or long-lived flags; not the same as framework version upgrades alone.
pn-deslop
Remove AI-generated code slop and clean up code style. Use in review passes and before shipping; part of the pn-review-optimize-loop.