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 pantheon-org/tekhne --skill vault-fetchgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/vault-fetch)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/vault-fetch"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/vault-fetch/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/pantheon-org/tekhne/vault-fetch"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/vault-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00525 |
| Opus 5 | $0.00031 | $0.00262 |
| Sonnet 5 | $0.00012 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
vault-fetch 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.
What it actually says
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: semanticandforceCapture: 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 tosemantic; 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://orlocalhostURLs — 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 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.
- evals/instructions.json 2.0 KB
- evals/scenario-1/capability.txt 18 B
- evals/scenario-1/criteria.json 1.1 KB
- evals/scenario-1/task.md 307 B
- evals/scenario-2/capability.txt 18 B
- evals/scenario-2/criteria.json 952 B
- evals/scenario-2/task.md 289 B
- evals/scenario-3/capability.txt 15 B
- evals/scenario-3/criteria.json 1.1 KB
- evals/scenario-3/task.md 332 B
- evals/scenario-4/capability.txt 15 B
- evals/scenario-4/criteria.json 878 B
- evals/scenario-4/task.md 281 B
- evals/scenario-5/capability.txt 12 B
- evals/scenario-5/criteria.json 941 B
- evals/scenario-5/task.md 308 B
- evals/summary_infeasible.json 58 B
- evals/summary.json 246 B
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 · 63 lines · 62 tokens per session scan A 04a9723feea8
vault-fetch is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 525 once invoked, about $0.0003 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
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
catchup
Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean. Use when the human returns after a gap, says they can't follow the project anymore, asks what happened or what a term means, or before deciding what to do next when their mental model…