Borrowing it
Nothing to install: this file belongs to RuloGB/compendio-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RuloGB/compendio-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/RuloGB/compendio-mcpWrote 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/rulogb/compendio-mcp/agents-md)<a href="https://agentmods.dev/instructions/rulogb/compendio-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rulogb/compendio-mcp/agents-md/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.
<a href="https://agentmods.dev/instructions/rulogb/compendio-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rulogb/compendio-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04076 | $0.04076 |
| Opus 5.5 | $0.01630 | $0.01630 |
| Sonnet 5.5 | $0.00815 | $0.00815 |
| Haiku 4.5 | $0.00408 | $0.00408 |
Grade A, and why
compendio-mcp AGENTS.md scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **DO NOT CHANGE: `cli.ts`'s entry-point guard uses `realpathSync`, not `realpathSync.native`** — `.native` breaks it on Windows 8.3 paths (exit 0, empty stdout). `test/cli-subprocess.test.ts` — [more](docs/design-decis How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to working with code in this repository.
Keeping this file small. This file is loaded into every agent session, so it holds only what an agent must know before touching code and cannot deduce from reading it — one line per item, with a pointer to where the detail lives (file + symbol, never a line number — those go stale).
Measurements, manual gates, before/after tables and history go to docs/ (docs/manual-gates.md, docs/design-decisions.md, docs/release-and-registry.md) or to the change's openspec/ artifacts.
Rationale that belongs to one piece of code goes in a comment next to that code. Do not repeat here what a code comment or a test already states.
What this is
Compendio is an MCP server that indexes a project's markdown documentation and exposes it to AI agents through local hybrid search (BM25/FTS5 + embeddings via RRF fusion). Everything runs locally: one SQLite file, embeddings on CPU (transformers.js), zero network calls at query time.
Commands
npm run build # compiles to dist/ (tsc)
npm test # vitest run — full suite
npm run test:watch # vitest watch mode
npx vitest run test/domain/chunking.test.ts # single file
npx vitest run -t "name of the test" # single test by name
npm run typecheck # tsc --noEmit
npm run dev -- <args> # run the CLI without compiling (tsx src/cli.ts)
There is no lint script configured.
Manual smoke test against the example corpus:
node dist/cli.js --root ejemplos index
node dist/cli.js --root ejemplos eval
node dist/cli.js --root ejemplos search "¿cuándo se considera duplicado un lead?"
- Manual gates (progress-bar smoke test, vector reach, fence handling, excerpt anchoring, chunk bound, word boundaries): procedures, expected numbers and RED verifications in
docs/manual-gates.md. Always runnode dist/cli.js, never a barecompendio(that resolves to the global npm install). - Releases and the MCP registry (
mcpName, namespace case,server.json,mcp-publisher):docs/release-and-registry.md.
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.
- 1mo ago Changed · +81 tokens per session d6c3a08cc2d2
- 1mo ago Changed · -462 lines · -12,600 tokens per session 2c979e78eede
- 1mo ago Changed · +31 lines · +609 tokens per session 6f0168b02e8d
- 1mo ago Changed · +164 lines · +3,948 tokens per session b033c77f7958
- 1mo ago First seen · 387 lines · 12,038 tokens per session scan A 644ed8348f83
compendio-mcp AGENTS.md is an instructions file published in the GitHub repository RuloGB/compendio-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 4,076 tokens to every session, about $0.0163 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.