What is langclaw-croo-agent?

A set of agent instructions for source-backed Web3 research, where Web3 means blockchain-based networks and applications. It covers onchain data, which is information recorded on a blockchain, as well as claim checks and builder reviews.

Use it to research protocols and tokens, inspect wallets or contracts, verify project claims, check readiness, review builder-program fit, or prepare agent-commerce submissions.

It gives the agent defined ways to research projects, inspect blockchain activity, and judge whether claims or applications are supported by sources.

langclaw-croo-agent — Skill by Langclaw-AI-CROO

Install

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.

Any agent

npx skills add Langclaw-AI-CROO/langclaw-croo-agent --skill skill

Clone the repo

git clone --depth 1 https://github.com/Langclaw-AI-CROO/langclaw-croo-agent

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/langclaw-ai-croo/langclaw-croo-agent/skill/github.svg)](https://agentmods.dev/skills/langclaw-ai-croo/langclaw-croo-agent/skill)

Your own site

<a href="https://agentmods.dev/skills/langclaw-ai-croo/langclaw-croo-agent/skill"><img src="https://agentmods.dev/badge/skills/langclaw-ai-croo/langclaw-croo-agent/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/langclaw-ai-croo/langclaw-croo-agent/skill"><img src="https://agentmods.dev/badge/skills/langclaw-ai-croo/langclaw-croo-agent/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 692 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.00092	$0.00692
Opus 5.5	$0.00037	$0.00277
Sonnet 5.5	$0.00018	$0.00138
Haiku 4.5	$0.00009	$0.00069

Measured 2mo ago against content hash a65b077e6510, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

langclaw-croo-agent 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 2mo 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.

Origin

This is a copy

100% identical to langclaw-croo-agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/mcp-client/assets/skill/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Langclaw CROO Agent

Use this skill when Langclaw should provide source-backed research through the MCP server.

Workflow

Use langclaw_readiness before live demo or provider work.
Use langclaw_research for broad research on protocols, projects, token topics, and agent ideas.
Use langclaw_onchain_intelligence for wallets, tokens, contracts, liquidity, TVL, transactions, bridges, governance, or protocol metrics.
Use langclaw_verify_claim when the user asks whether a specific claim is supported.
Use langclaw_builder_review when the user asks whether a project matches a builder program, hackathon, grant, or submission.
Treat low confidence output as a draft and ask for stronger provider configuration before final decisions.

Slash-Style Commands

When the user types one of these commands, call the matching Langclaw MCP tool:

/langclaw <query>: use langclaw_command or langclaw_research.
/langclaw-research <query>: use langclaw_command or langclaw_research.
/langclaw-onchain <query>: use langclaw_command or langclaw_onchain_intelligence.
/langclaw-verify <claim>: use langclaw_command or langclaw_verify_claim.
/langclaw-builder-review <project>: use langclaw_command or langclaw_builder_review.
/langclaw-readiness: use langclaw_command or langclaw_readiness.

Examples:

/langclaw-research CROO agent market fit
/langclaw-onchain Base smart money last 7 days
/langclaw-builder-review Review this repo for CROO
/langclaw-verify Langclaw supports hosted MCP access
/langclaw-readiness

Output Rules

Keep conclusions short.
Cite the source titles and URLs returned by the MCP tool.
Separate facts, caveats, and recommendations.
Do not invent provider results.
Do not call the CROO provider unless the user asks to run or test provider flow.
Reject requests that require signing, swaps, approvals, custody, or value transfer.
If the user sends an onchain-style prompt through broad research, expect the core agent to auto-route it to onchain intelligence.

Read the full file on GitHub · 58 lines

Changes

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.

2mo ago First seen · 58 lines · 92 tokens per session scan A a65b077e6510

Subscribe to this mod's changes

langclaw-croo-agent is a skill published in the GitHub repository Langclaw-AI-CROO/langclaw-croo-agent (0 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 692 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to langclaw-croo-agent, differing in 0 lines, and is treated as a copy.

Research Web3 and blockchain

langclaw-croo-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
langclaw-croo-agentLangclaw-AI-CROO/langclaw-croo-agent	Skill	0	4mo ago	MIT	A	92	Claude Code, Codex
signature-replayPurpleAILAB/Decepticon	Skill	6.5k	9d ago	Apache-2.0	A	31	Claude Code, Codex
bridgealsk1992/CloddsBot	Skill	3.1k	yesterday	MIT	A	13	Claude Code, Codex
onchainkitalsk1992/CloddsBot	Skill	3.1k	yesterday	MIT	A	24	Claude Code, Codex
marginfialsk1992/CloddsBot	Skill	3.1k	yesterday	MIT	A	11	Claude Code, Codex
official-sui-skillsMystenLabs/sui	Skill	7.8k	today	Apache-2.0	A	116	Claude Code, Codex
devtools-event-clientTanStack/devtools	Skill	512	yesterday	MIT	A	79	Claude Code, Codex