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/web3dev1337/gastown-gui/claude-mdgit clone --depth 1 https://github.com/web3dev1337/gastown-guiWrote 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/web3dev1337/gastown-gui/claude-md)<a href="https://agentmods.dev/instructions/web3dev1337/gastown-gui/claude-md"><img src="https://agentmods.dev/badge/instructions/web3dev1337/gastown-gui/claude-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 | $0.00932 | $0.00932 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
gastown-gui 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Gas Town GUI
Web GUI for steveyegge/gastown multi-agent orchestrator.
READ THESE ENTIRE DOCUMENTS BEFORE DOING ANYTHING
- Read
CODEBASE_DOCUMENTATION.mdNOW — Complete file inventory. Do NOT grep blindly for files. Read this first so you know where everything lives. - Read
CLI-COMPATIBILITY.md— Which gt/bd commands work, which are broken/remapped. Critical if touching any CLI calls.
Update before PR: If you added/deleted/moved files, update CODEBASE_DOCUMENTATION.md.
Overview
Browser SPA (vanilla JS, no framework) backed by an Express server that wraps gt/bd CLI commands as HTTP endpoints. WebSocket streams real-time events from gt feed. Published to npm as gastown-gui.
Architecture
- Entry:
server.js— monolith Express server, partially refactored intoserver/modules - Refactored path: Gateway → Service → Route (see
server/gateways/,server/services/,server/routes/) - Legacy endpoints: Mail, agents, nudge, polecat control, service controls still inline in
server.js - CLI safety: All commands use
execFile(no shell) +SafeSegmentinput validation - Frontend: Vanilla JS in
js/, components render via innerHTML, global state injs/state.js - Real-time: WebSocket client in
js/api.js, server pipesgt feed --jsonoutput - CLI entry:
bin/cli.js— supportsstart,doctor,version,help
File Size Discipline
- No god files/classes: Do not keep adding logic to large files (especially
server.js). - Extract by responsibility: New backend logic should be placed in focused modules under
server/(services/gateways/routes/infrastructure) and imported intoserver.js. - Refactor when touching: If a change makes a file larger or more complex, extract helpers into dedicated files in the same PR.
Commands
npm start # Start server (port 7667)
npm run dev # Dev mode with auto-reload
npm test # All tests (unit + integration + e2e)
npm run test:unit # Unit tests only
npm run test:e2e # E2E tests only (needs Puppeteer)
npm run test:watch # Watch mode
npm run test:ui # Vitest UI
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.
- 4d ago First seen · 62 lines · 932 tokens per session scan A 4ae66c804e6e
gastown-gui CLAUDE.md is an instructions file published in the GitHub repository web3dev1337/gastown-gui (87 stars, last pushed 4d ago), licensed MIT. It adds 932 tokens to every session, about $0.0047 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
deer-flow copilot-instructions.md
Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
codex-acp-bridge AGENTS.md
Instructions for normahq/codex-acp-bridge, covering codex-acp-bridge — agents.md, development standards, quality gates (required), logging policy and bridge guardrails.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
vant AGENTS.md
AGENTS.md instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.
harness AGENTS.md
AGENTS.md instructions for puristajs/harness, covering agent guidance, source of truth, repository rules, expected commands and implementation rules.