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 commands/coinyak/onchainai/find-toolgit clone --depth 1 https://github.com/Coinyak/onchainaiWrote 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/commands/coinyak/onchainai/find-tool)<a href="https://agentmods.dev/commands/coinyak/onchainai/find-tool"><img src="https://agentmods.dev/badge/commands/coinyak/onchainai/find-tool.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00317 |
| Opus 5 | $0.00008 | $0.00159 |
| Sonnet 5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
find-tool 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 5d 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
Use the free onchainai MCP search_tools tool (public
https://www.onchain-ai.xyz/mcp — not /mcp/okx) to find tools matching: $ARGUMENTS
Summarize the top 3 results with name, purpose, chains, type, install risk,
and x402/paid status. Prefer free get_tool_detail for trust and payment
metadata. Do not call premium tools (export_toolkit, recommend_verified_tool,
gap_audit ~$0.01; check_endpoint_health ~$0.001) unless the user asks and
the client can settle x402 — Claude Code often cannot. Then offer install steps
via get_install_guide for the user's agent. Never recommend a critical-risk tool.
If the user asks to save or add a tool to their OnchainAI toolkit, call
save_to_toolkit with the slug (only after explicit consent). If the MCP
response includes link_required, tell them to link at
https://www.onchain-ai.xyz/connect#agent-sync and set ONCHAINAI_AGENT_TOKEN
in their MCP config (see plugin .mcp.json).
For multi-tool workflows, offer save_stack_to_blueprint after the user
confirms — it saves to toolkit and today's agent session blueprint.
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.
- 5d ago First seen · 24 lines · 15 tokens per session scan A 931c0fa32aec
find-tool is a command published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 317 once invoked, about $0.0001 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 commands, from other repositories
new-solana
Scaffold a new Solana Anchor program.
rpc
List RPC endpoints and chain profiles.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.