enquire-mcp: Instructions file for Claude Code

CLAUDE.md

enquire-mcp CLAUDE.md is an instructions file for Claude Code from oomkapwn/enquire-mcp. It costs 8,186 tokens per session, scanned A, original, MIT.

A repository instruction file describing the current work, release requirements, audit checkpoints, non-goals, and testing context for an MCP server. An MCP server is a program that exposes tools and resources to AI clients.

In plain words
What is it for?
Use it when changing the server, preparing release candidates, checking CI and CodeQL results, reviewing tests, or deciding whether distribution work is in scope.
Why use it?
It gives coding agents the project’s current constraints so they do not treat old release results or deferred work as current approval.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is oomkapwn/enquire-mcp's own configuration. It tells Claude Code how to work on enquire-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything enquire-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/oomkapwn/enquire-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oomkapwn/enquire-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for enquire-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oomkapwn/enquire-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/oomkapwn/enquire-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oomkapwn/enquire-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/oomkapwn/enquire-mcp/claude-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.

agentmods 80×15 button for enquire-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oomkapwn/enquire-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/oomkapwn/enquire-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,186 This file is loaded in full into every session.
When invoked 8,186 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08186 $0.08186
Opus 5.5 $0.03274 $0.03274
Sonnet 5.5 $0.01637 $0.01637
Haiku 4.5 $0.00819 $0.00819

Measured 5d ago against content hash bfd375fce409, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

enquire-mcp 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 5d 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.

CLAUDE.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project goal — v4 MCPB Basic candidate + audit-driven hardening line

This file is read by Claude Code sessions on this repo. It defines the current sprint goal, scope, quality bar, and anti-patterns so any session (continuation or new) shares the same North Star.

Current state (as of 2026-10-04): tracked source is v4.0.0-rc.7. The reviewed starting main is ceb20d4 (PR #622). Three PRs landed on 2026-10-03: #623 carried the one unavoidable source-tree dependency exception (GHSA-86w9-cpqp-85rv, node-forge — no patched release exists; the only dependent is the dev-only @anthropic-ai/mcpb; tracker digitalbazaar/forge#1149) and made that waiver dev-only by construction after an independent review showed it was silently covering the production graph; #621 shipped the tooling phase's test-count cascade; #622 committed the mutation-helper census reproduction. The September line added final-response recall fallback, schema-v7 identifier parts in a separate chunk_parts table, shared erasure receipts, clear-feedback, and cursor-based resources/list. Its hosted CI, CodeQL and Pages completed successfully; those historical results do not substitute for CI on a new candidate. The bounded T-Search protocol remains retained without a server-side LLM: 47 tools · 19 prompts · 2367 tests · 11 languages. Distribution remains deferred pending distribution readiness and explicit resumption; rc.7 is untagged and unpublished. The last verified package channels were @latest v3.11.6 and @rc v4.0.0-rc.3; recheck the registry when publication resumes.

Active work (2026-10-04): a full-project static and live-repository audit at ceb20d4 has opened safety and correctness follow-ups; green historical CI is not proof that the newly identified scenarios are covered. The continuation order now prioritizes write/rollback preservation and exact persistence-target authority → generation-consistent hybrid retrieval and bounded embedding inputs → resource-pagination identity/cursor/work bounds → tooling/control truth (T, then AH-7) → bounded optional acquisition (AH-8) → Russian/PDF work. Each product slice needs a causal positive control, a negative control that fails on the old behavior, independent review, exact-candidate hosted CI, and an exact-main re-sweep. T1 implementation landed (#621), but its partial-drift check still needs a regression; T4 is a diagnostic, not a gate, with measured differences still unresolved. The earlier T-first queue is superseded by this risk-driven order. AH-4, AH-5 and AH-6 implementation remains landed, not flawless. Keep one product change active. Local package installation, build, lint, tests, coverage, OIA, smoke and benchmarks remain excluded; executable validation belongs to GitHub-hosted CI. Distribution remains parked. Use a current non-cloud-synced checkout, compare notes with GitHub, and retain historical release material in CHANGELOG.md and Git history. Do not publish private coordination notes or personal workspace/account details.

  • v4.0.0-rc.7 full-audit safety closure plus AH-4 staged replacement; rc.6 remains tagged but unpublished: ambiguous and late-occupant rename rollback fails closed with append-only recovery; query/eval recognize shared FTS aliases by physical identity; tag/link evidence is complete but bounded; graph claims match the equal-RRF candidate in-degree tie-break; HNSW cleanup removes same-or-older invalidated DB authorities under the publisher lease, including no-receipt failures. Configuration-changing embedding builds now validate a complete private generation before atomic promotion and preserve the prior usable generation on pre-promotion failure. 2228 → 2367 source tests.
  • v4.0.0-rc.6 A6 recovery, tagged but unpublished: version surfaces and public acquisition strings name 4.0.0-rc.6. Release handoff copies the body to release-notes.md instead of a same-file mv; the annotated tag exists, but OIDC publication failed with ENEEDAUTH, so npm @rc and GitHub Releases remain at rc.3. A7 remains HOLD on unpublished typescript-sdk#2574. 2228 → 2228 source tests.
  • v4.0.0-rc.5 tagged but unpublished predecessor: squash-main 5438622; annotated tag exists; GitHub Release and npm @rc were not published. 2228 → 2228 source tests.
  • v4.0.0-rc.4 unpublished full-audit source predecessor: read-only verification, three consequence-separated publication jobs, exact CI-built artifact handoff, reproducible Docker, and the audited runtime/persistence closures were staged but never tagged. 1807 → 2228 source tests.
  • v4.0.0-rc.3 published predecessor — shipped the post-rc.2 hardening line through the tag-push-only protected controller; exact npm/GitHub release source 3edcba4c6b1de813686601c36c1c2b487e20e382. 1807 → 1807 source tests.
  • v4.0.0-rc.2 published Basic MCPB predecessor — packages the bounded 13-tool read-only profile, adds exact-byte three-OS consumer evidence, transparency sidecars, and a fail-closed twelfth release context while preserving the full edition defaults. 1807 → 1807 source tests.
  • v4.0.0-rc.1 shipped SDK-v2 foundation — exact v2 packages, dual-era transports, write-safe shutdown, official-client conformance, and packed-consumer matrices; exact tag/npm gitHead 4af28086d30ab08fefce49d94107c18c14eac18f. 1795 → 1807 source tests.

Read the full file on GitHub · 105 lines

Changes

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.

  1. 5d ago Changed bfd375fce409
  2. 6d ago Changed c25622b70ee5
  3. 8d ago Changed 7c203d6d0eec
  4. 9d ago Changed 2928313bf9e6
  5. 12d ago Changed 7333ddbcba4d
  6. 13d ago Changed cf6087d1e5e3
  7. 14d ago Changed f6501c163345
  8. 24d ago Changed · +173 tokens per session d5adfd7f5351
  9. 26d ago First seen · 105 lines · 8,013 tokens per session scan A 85f6d7e00334

Subscribe to this mod's changes

enquire-mcp CLAUDE.md is an instructions file published in the GitHub repository oomkapwn/enquire-mcp (34 stars, last pushed 4d ago), licensed MIT. It adds 8,186 tokens to every session, about $0.0327 per session on Opus 5.5. 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 2026-10-02.

Related

Other instructions, from other repositories