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 instructions/crabwise-ai/crabwalk/agents-mdgit clone --depth 1 https://github.com/crabwise-ai/crabwalkWrote 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/instructions/crabwise-ai/crabwalk/agents-md)<a href="https://agentmods.dev/instructions/crabwise-ai/crabwalk/agents-md"><img src="https://agentmods.dev/badge/instructions/crabwise-ai/crabwalk/agents-md.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 5.1 | $0.00707 | $0.00707 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
crabwalk AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/routes/: TanStack Start file-based routes (/monitor,/workspace, API handlers undersrc/routes/api/).src/components/: UI by domain (monitor/,workspace/,navigation/,ani/).src/integrations/: external/system integrations (openclaw/,trpc/,query/).src/lib/: shared utilities (graph layout, workspace FS helpers, demo data).public/: static assets (images, fonts, skill metadata).- Runtime and packaging files:
Dockerfile,docker-compose.yml,bin/crabwalk.
Architecture Overview
- Stack: TanStack Start + Router, tRPC, TanStack Query/DB, ReactFlow, Tailwind v4, React 19.
- Monitor flow: OpenClaw gateway WebSocket -> server integration (
src/integrations/openclaw/) -> tRPC router (src/integrations/trpc/router.ts) -> client collections/graph UI. - API entrypoint:
src/routes/api/trpc.$.ts; router setup insrc/router.tsx.
Build, Test, and Development Commands
npm run dev: starts local dev server onhttp://localhost:3000.npm run build: creates production build with Vite/TanStack Start.npm start: runs the built server from.output/server/index.mjs.docker-compose up -d: run containerized app (setCLAWDBOT_API_TOKENfirst).
Coding Style & Naming Conventions
- Language: TypeScript + React function components.
- Style in current codebase: 2-space indentation, single quotes, semicolon-light formatting.
- Components/files:
PascalCasefor React components (example:SessionNode.tsx). - Hooks/utilities:
camelCaseexports, hooks prefixed withuse(example:useIsMobile.ts). - Route files follow TanStack conventions, e.g.
src/routes/monitor/index.tsx,src/routes/api/trpc.$.ts. - Use path alias
~/for imports fromsrc.
Testing Guidelines
- No dedicated automated test script is currently defined in
package.json. - Minimum pre-PR validation: run
npm run build, then verify/monitorconnectivity and/workspacefile operations innpm run dev. - If adding tests, colocate as
*.test.ts/*.test.tsxnear the feature and prefer fast unit tests for parsing/state logic.
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.
- 6d ago First seen · 47 lines · 707 tokens per session scan A b573c3af0020
crabwalk AGENTS.md is an instructions file published in the GitHub repository crabwise-ai/crabwalk (878 stars, last pushed 1mo ago), licensed MIT. It adds 707 tokens to every session, about $0.0035 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 instructions, from other repositories
openclaw-kubernetes AGENTS.md
Instructions for feiskyer/openclaw-kubernetes, covering agents.md, links, development commands, lint the chart against all values files and render templates to verify correctness (output discarded).
autoclaw.sh AGENTS.md
Instructions for datopian/autoclaw.sh, covering agent instructions, quick reference, landing the plane (session completion), issue tracking with bd (beads) and why bd?.
openclaw-kubernetes CLAUDE.md
Instructions for feiskyer/openclaw-kubernetes, covering claude.md, links, development commands, lint the chart against all values files and render templates to verify correctness (output discarded).
RuView AGENTS.md
AGENTS.md instructions for ruvnet/RuView, covering ruview repository instructions for codex, operating contract, repository map, ruview contributor harness and homecore metaharness.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.