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/vikasprogrammer/walkie/claude-mdgit clone --depth 1 https://github.com/vikasprogrammer/walkieWhat 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 | $0.01829 | $0.01829 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
walkie CLAUDE.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 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
walkie — P2P communication CLI for AI agents. npm package: walkie-sh.
Architecture
bin/walkie.js— CLI entry point (commander). Version is here AND inpackage.json(keep in sync)src/api.js— Programmatic API (require('walkie-sh')). Exportslisten()andsend(). Uses daemon IPC under the hood.src/daemon.js— background daemon managing Hyperswarm P2P + local subscriber routingsrc/client.js— IPC client, handles daemon auto-start and stale socket cleanupsrc/crypto.js— topic derivation (SHA-256 of channel+secret)src/cli-utils.js— identity resolution (WALKIE_ID>~/.walkie/config.json> terminal session), channel arg parsing, message filterssrc/slack.js— Slack <-> walkie bridge over Socket Mode (walkie slack)src/web.js— HTTP + WebSocket server bridging browser clients to daemonsrc/web-ui.js— exports HTML string for web chat UI (minimal, terminal-style)
Programmatic API
package.json "main" points to src/api.js. Node apps can require('walkie-sh'):
const walkie = require('walkie-sh')
// Listen on a channel (EventEmitter — emits 'message' and 'error')
const ch = await walkie.listen('mychannel:secret', { id: 'mybot' })
ch.on('message', async (msg) => {
// msg: { from: string, data: string, ts: number, id: string }
await ch.send('response')
})
await ch.close()
// One-shot send (auto-joins if secret provided)
await walkie.send('mychannel:secret', 'hello', { id: 'sender' })
listen()joins the channel, starts streaming viastreamMessages(), filters own messages, returns aWalkieChannel(EventEmitter +send()+close())send()auto-joins and fires a single message — good for scripts/CI- Both auto-start the daemon if not running
Testing
npm test — 53 automated tests using node:test (zero extra deps). Covers crypto, store, CLI utils, daemon IPC, web server, and programmatic API.
npm run test:p2p — manual P2P integration test (two daemons, Hyperswarm discovery, ~30s).
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 · 138 lines · 1,829 tokens per session scan A e45b8056000c
walkie CLAUDE.md is an instructions file published in the GitHub repository vikasprogrammer/walkie (250 stars, last pushed 8d ago), licensed MIT. It adds 1,829 tokens to every session, about $0.0091 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
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.