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 agentmods add skills/vaayne/agent-kit/agent-librariannpx skills add vaayne/agent-kit --skill agent-librariangit clone --depth 1 https://github.com/vaayne/agent-kitWhat 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 | $0.00103 | $0.00314 |
| Opus 5 | $0.00051 | $0.00157 |
| Sonnet 5 | $0.00021 | $0.00063 |
| Haiku 4.5 | $0.00010 | $0.00031 |
Grade A, and why
agent-librarian 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 2d 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
Agent Librarian
Spawn a subagent to read and explain external repositories. Give it access hints:
gh CLI for issues/PRs/files, or a shallow git clone --depth 1 into a temp dir for
whole-repo reading.
When not to use
- Local workspace code you can fully read — use direct tools or agent-finder.
- A simple lookup answerable by fetching one URL or one
ghcommand yourself. - Code modifications — this role is read-only understanding.
How to write the task
- Name the repository or project when you know it; include the ref/version if it matters (a vendored copy is not the source of truth for the layer you describe).
- Ask a specific question or describe the feature/codepath to understand, plus what you are trying to achieve with the answer.
- Ask for a thorough answer with file paths and evidence, suitable for reuse — return it in full rather than re-summarizing.
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.
- 2d ago First seen · 26 lines · 103 tokens per session scan A 6fca6aeb1555
agent-librarian is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 314 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
add-resend
Add Resend (email) channel integration via Chat SDK.
codegen
Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
optimize-agentic-workflow
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.