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/autoworks-ai/autovaultnpx agentmods add skills/autoworks-ai/autovault/autovault-skillWrote 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/autovault-skill)<a href="https://agentmods.dev/skills/autoworks-ai/autovault/autovault-skill"><img src="https://agentmods.dev/badge/skills/autoworks-ai/autovault/autovault-skill/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/autovault-skill"><img src="https://agentmods.dev/badge/skills/autoworks-ai/autovault/autovault-skill.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 | $0.00084 | $0.02612 |
| Opus 5 | $0.00042 | $0.01306 |
| Sonnet 5 | $0.00017 | $0.00522 |
| Haiku 4.5 | $0.00008 | $0.00261 |
Grade B, and why
autovault-skill scanned grade B with 2 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 12d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -l ~/.claude/skills Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
declaring `network: false` that contains `curl`/`wget`/`fetch` is How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoVault Meta-Skill
AutoVault is the local capability and skill profile layer. It stores and validates skills, then syncs them into the agent's normal skill directory as filesystem symlinks. If this skill is loaded, AutoVault profile sync is already working for this agent; do not require an AutoVault MCP server before using other visible skills.
AutoVault does not execute skills. The agent that loads a skill is responsible for sandboxing and user confirmation before running anything the skill describes.
Hard rule: never write the vault by hand
~/.autovault/skills/<name>/ is a signed store, not a working copy.
Hand-editing SKILL.md there invalidates the Ed25519 manifest
(autovault doctor <name> reports tampered / signature_invalid).
autovault sync-profiles only refreshes symlinks. It does not validate,
hash, or re-sign.
Author or edit a bundle outside the vault (a temp directory is fine), then install through the same gate humans and MCP use:
# New skill, or replace an existing one by frontmatter name
autovault add-local /path/to/bundle --sync-profiles
# Preserve recorded provenance when replacing a local skill
autovault add-local /path/to/bundle --source '<existing-identifier>' --sync-profiles
Confirm the vault accepted the write:
autovault doctor <name> --json # integrity.kind must be "ok"
If MCP tools are connected, propose_skill (new) and update_skill (existing)
are the same gate. Use them when present. When they are absent the CLI is
required, not optional. autovault doctor <name> --repair re-signs a
tampered local bundle only. Remote-sourced skills (GitHub, agentskills,
URL) must be reinstalled or updated from upstream. Repair is a recovery hatch,
not the authoring path.
When to use
- When the user asks why an AutoVault-managed skill is visible.
- When deciding whether to use a synced skill such as
commit-messageorskill-author. - Before writing or updating a skill. Check installed skills first
(
autovault skill search <query>or the host's skill list). - When
autovault doctorreports tampered integrity. - When debugging profile sync or stale skill links.
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.
- 12d ago First seen · 247 lines · 84 tokens per session scan B 8ad68b94cd0d
autovault-skill is a skill published in the GitHub repository autoworks-ai/autovault (4 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 2,612 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). 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.
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.
aws-lambda-typescript-integration
Provides AWS Lambda integration patterns for TypeScript with cold start optimization. Use when creating or deploying TypeScript Lambda functions, choosing between NestJS framework and raw TypeScript approaches, optimizing cold starts, configuring API Gateway or ALB integration, or implementing serverless TypeScript…
aws-cdk
Provides AWS CDK TypeScript patterns for defining, validating, and deploying AWS infrastructure as code. Use when creating CDK apps, stacks, and reusable constructs, modeling serverless or VPC-based architectures, applying IAM and encryption defaults, or testing and reviewing cdk synth, cdk diff, and cdk deploy…