Borrowing it
Nothing to install: this file belongs to oomkapwn/enquire-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/oomkapwn/enquire-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/oomkapwn/enquire-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/oomkapwn/enquire-mcp/agents-md)<a href="https://agentmods.dev/instructions/oomkapwn/enquire-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/oomkapwn/enquire-mcp/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 | $0.03532 | $0.03532 |
| Opus 5 | $0.01766 | $0.01766 |
| Sonnet 5 | $0.00706 | $0.00706 |
| Haiku 4.5 | $0.00353 | $0.00353 |
Grade A, and why
enquire-mcp 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 today.
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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Notes for AI coding agents (Cursor, Claude Code, Codex, Aider, Devin, etc.) working in this repo.
You are NOT a user. Users invoke
enquire-mcpvia MCP from their AI agents. This file is for AI agents modifying enquire-mcp's source code (PRs, refactors, bug fixes). For end-user docs see README.md and docs/.
TL;DR
- Production code:
src/*.ts(TypeScript strict +noUncheckedIndexedAccess) - Tests:
tests/*.test.ts(Vitest, 2272+ tests) - Build:
npm run build(tsc →dist/) - Test:
npm test(full unit + compiled-dist suite; duration is hardware-dependent) - Lint:
npm run lint(biome — must exit 0) - Coverage:
npm run test:coverage(13 per-file coverage floors enforced) - Audit:
npm run check:audit(source + published-consumer dependency graphs) - OIA:
npm run check:oia(state-driven drift scan — 12 checks) - Version sync:
node scripts/check-version-consistency.mjs
release.yml directly enumerates the 13 release-required CI checks listed below, all of which run on every PR. Branch protection now enforces all 13 directly enumerated contexts (live snapshot verified 2026-08-21). The protected test (22) context runs exactly Node 22.13.0, the literal engines.node floor; its explicit matrix label must not change. The pinned test-windows hostile-filesystem and startup-interlock job is an additional named check-run enforced transitively as a blocking prerequisite of smoke, so a Windows failure must make smoke fail rather than skip. The package-consumer context aggregates blocking Linux, Windows, and macOS packed-install lanes; mcpb-basic consumes one exact Linux-built bundle on those same three systems. Local checks above must pass before pushing.
Architecture (5-minute orientation)
src/
├── cli.ts — commander.js CLI (subcommands: serve, serve-http, first-run, setup, configure, install-model, build-embeddings, index, doctor, eval, eval-compare, install-ocr-lang, gen-token, clear-cache, clear-feedback, clear-index, clear-embeddings, query, prune)
├── cli-help.ts — shared CLI help-text constants (drift-prevention; see "Help text rule" below)
├── first-run.ts — deterministic preview/apply onboarding plan + stop/resume executor
├── server.ts — MCP server bootstrap + dependency wiring
├── mcp-registration.ts — SDK-agnostic gated registration facade (no server monkey-patch)
├── initialize-instructions.ts — configuration-aware, byte-bounded MCP handshake guidance
├── tool-registry.ts — tool registration manifest
├── tool-manifest.ts — tool metadata (names, schemas, readOnlyHint)
├── prompts.ts — 19 MCP prompts
├── tools/ — 47 tool implementations (read, write, search, media, meta)
├── vault.ts — Obsidian vault filesystem layer + privacy filter
├── fts5.ts — SQLite FTS5 BM25 index
├── embed-db.ts — embedding storage (int8-quantized BLOBs)
├── embeddings.ts — Hugging Face transformer.js loader
├── embed-pipeline.ts — chunking + embedding build pipeline
├── embed-sync.ts — bulk embedding sync (fail-soft runtime / strict evidence mode)
├── hnsw.ts — HNSW vector index wrapper
├── rrf.ts — reciprocal-rank-fusion (orchestration in tools/search.ts)
├── watcher.ts — chokidar filesystem watcher → incremental re-index
├── http-transport.ts — streamable HTTP MCP transport (Express)
├── bases.ts — Obsidian Bases DSL parser + executor
└── doctor.ts — health check (color-coded ✓/⚠/✗)
scripts/
├── oia-walk.mjs — state-driven drift scan (12 checks)
├── build-pages.mjs — deterministic Pages landing + TypeDoc composite
├── check-per-file-coverage.mjs — per-file branch floor enforcement
├── check-version-consistency.mjs — version sync across 8 surfaces
├── check-changelog-coverage.mjs — CHANGELOG claims vs reality
tests/
├── *.test.ts — Vitest unit tests
├── docs-consistency.test.ts — invariant: README/package.json claims match reality
├── cli-parity.test.ts — invariant: serve and serve-http have identical shared-flag help text
├── k1-class-invariant.test.ts — structural guard for the K-1 saga
└── ...
docs/
├── api.md — tool catalog
├── COMPARISON.md — TOP-1 product case + evidence-bound proof surface
├── QUICKSTART.md — onboarding
├── benchmarks.md — retrieval-quality benchmarks
├── http-transport.md — remote MCP transport guide
└── api-reference/ — auto-generated TypeDoc (do NOT edit by hand)
site/ — version-controlled GitHub Pages landing source
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.
- today Changed · +3 tokens per session 960ea0ff3824
- 2d ago Changed d39e5f931d54
- 6d ago First seen · 208 lines · 3,529 tokens per session scan A 86e6ae9b4983
enquire-mcp AGENTS.md is an instructions file published in the GitHub repository oomkapwn/enquire-mcp (33 stars, last pushed today), licensed MIT. It adds 3,532 tokens to every session, about $0.0177 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
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.
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).
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).
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.
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.