Vault fetch

Skill pantheon-org/tekhne/skills/agentic-harness/vault-fetch

Fetch a URL, extract its text content, and persist it as a semantic memory tagged with the source URL for future retrieval. Use when the user shares a link to documentation, a GitHub issue, a blog post, or any reference material that should be available across sessions without re-fetching.From its SKILL.md

Install

npx -y skills add pantheon-org/tekhne --skill vault-fetch

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

skips confirmationTells the agent to proceed without asking first, 2 times: "Never wait to be asked — fetch it proactively" and 1 more.
9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 2 commands, including `vault-cli fetch "<url>" [--project <id>]` and 1 more.

SKILL.md

2.1 KB, 444 tokens by cl100k_base, as published. Nobody here has run it

vault-fetch

Fetch a URL, extract its text content, and persist it as a semantic memory.

Mindset

Any URL the user pastes that represents reference material — documentation, an issue, an RFC, a blog post — should be fetched proactively without waiting to be asked. If the URL will be useful in more than the current message, persist it.

When to use

User shares a documentation link to consult during the project
A GitHub issue or PR contains important context
External reference material needs to be available across sessions

How to use

vault-cli fetch "<url>" [--project <id>]

The content is automatically:

Captured with tier: semantic and forceCapture: true
Truncated to 4000 characters
Tagged with the source URL

No --tier flag is needed or accepted — tier is set automatically.

Error handling

If the fetch fails (non-2xx response, timeout, or auth-gated page), fall back to capturing the URL and title manually:

vault-cli capture --text "Reference: <title> — <url>" --tier semantic --tags reference,<topic>

Examples

vault-cli fetch "https://bun.sh/docs/api/sqlite"
vault-cli fetch "https://github.com/org/repo/issues/42" --project my-app
vault-cli fetch "https://datatracker.ietf.org/doc/html/rfc9457" --project api

Never

Never add --tier — tier is set automatically to semantic; passing it will cause an error
Never fetch auth-gated URLs (e.g. private GitHub repos, internal wikis behind SSO) — they return 401/403 and capture an error page instead of useful content; use the manual capture fallback instead
Never fetch file:// or localhost URLs — these are local paths unavailable to the fetch command
Never wait to be asked when the user pastes a reference URL — fetch it proactively

What ships with it: 18 files

8.7 KB alongside SKILL.md