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/prgmr99/agora/claude-mdgit clone --depth 1 https://github.com/prgmr99/agoraWrote 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/prgmr99/agora/claude-md)<a href="https://agentmods.dev/instructions/prgmr99/agora/claude-md"><img src="https://agentmods.dev/badge/instructions/prgmr99/agora/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 5.1 | $0.00696 | $0.00696 |
| Opus 5 | $0.00348 | $0.00348 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
agora 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
npm install # Install dependencies
npm run build # Compile TypeScript → dist/
npm run dev # Watch mode (tsc --watch)
npm test # Run all tests (vitest)
npm run test:watch # Watch test mode
npm run lint # Type check only (tsc --noEmit)
npm run lint:eslint # ESLint check
npm run serve # Start MCP server via node dist/server.js
Run a single test file:
npx vitest run tests/matcher.test.ts
Pre-commit hook runs npm run lint → lint-staged (eslint --fix on staged .ts) → npm test.
Architecture
Agora is an MCP server that acts as a smart task router for AI agents. Agents register their capabilities; when a task is created, Agora keyword-matches it to the best agent and tracks the lifecycle.
Three-layer structure:
-
src/tools.ts— 8 MCP tool handlers (agora_register_agent,agora_unregister_agent,agora_list_agents,agora_find_agent,agora_create_task,agora_get_task,agora_list_tasks,agora_cancel_task). All inputs are validated with Zod schemas inline. -
src/matcher.ts— Keyword scoring engine. Tokenizes text, strips stopwords, then scores each agent capability by name (weight ×3), tags (×2), description (×1). ReturnsMatchResult[]sorted by normalized confidence (0–1). No ML/embeddings — pure keyword overlap. -
src/db.ts— SQLite viabetter-sqlite3with WAL mode.AgoraDBclass holds all prepared statements. Two tables:agents(capabilities/transport as JSON columns) andtasks(full lifecycle + assignment + match metadata).
Entry points:
src/server.ts— CreatesMcpServer, registers tools, connects viaStdioServerTransportsrc/cli.ts—agora init(writes~/.agora/config.json+ SQLite DB, auto-discovers Claude Desktop / Cursor /.mcp.json) andagora servebin/agora.js— CLI shim
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 · 51 lines · 696 tokens per session scan A eddcb87126c1
agora CLAUDE.md is an instructions file published in the GitHub repository prgmr99/agora (0 stars, last pushed 5mo ago), licensed MIT. It adds 696 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).