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-findernpx skills add vaayne/agent-kit --skill agent-findergit 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 | $0.00106 | $0.00300 |
| Opus 5 | $0.00053 | $0.00150 |
| Sonnet 5 | $0.00021 | $0.00060 |
| Haiku 4.5 | $0.00011 | $0.00030 |
Grade A, and why
agent-finder 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 Finder
Spawn a search subagent for one cohesive discovery question.
When not to use
- You know the exact file path — read it directly.
- You want a specific symbol or exact string — a scoped
rgis faster and cheaper. - The answer needs one search — a subagent spawn costs more than it saves.
How to write the task
- One call per cohesive question; batch related sub-questions into a single task instead of spawning per step.
- Phrase it as a precise engineering request: "Find every place we build an HTTP error response", not "error handling search".
- Name concrete artifacts, patterns, or APIs to narrow scope ("Express middleware", "fs.watch debounce"), and scope to directories when you can.
- State explicit success criteria so the subagent knows when to stop: "Return file paths and line numbers for all JWT verification calls".
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 · 106 tokens per session scan A a035027a107d
agent-finder is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 6d ago), licensed MIT. It adds 106 tokens to every session and 300 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
skillify
Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack).
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.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
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.
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.