mcp-custos: Instructions file for Claude Code

CLAUDE.md

mcp-custos CLAUDE.md is an instructions file for Claude Code from an0malous/mcp-custos. It costs 748 tokens per session, scanned A, original, MIT.

A project guide for mcp-custos, an MCP server that provides secure-coding and compliance reference material such as ISO, NIST, and OWASP guidance.

In plain words
What is it for?
It helps create and review features through steering documents, requirements, designs, task lists, and review records.
Why use it?
It gives development work a documented review path, including project context, feature specifications, templates, and human approval points.

Instructions file for Claude Code

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

This is an0malous/mcp-custos's own configuration. It tells Claude Code how to work on mcp-custos 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 mcp-custos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to an0malous/mcp-custos. 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/an0malous/mcp-custos/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/an0malous/mcp-custos

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 mcp-custos CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/an0malous/mcp-custos/claude-md.svg)](https://agentmods.dev/instructions/an0malous/mcp-custos/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/an0malous/mcp-custos/claude-md"><img src="https://agentmods.dev/badge/instructions/an0malous/mcp-custos/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 748 This file is loaded in full into every session.
When invoked 748 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 $0.00748 $0.00748
Opus 5 $0.00374 $0.00374
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 7d ago against content hash a7b6c2c65d56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-custos 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 7d 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 · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — agent guide

mcp-custos is an MCP server exposing secure-coding and compliance reference data (ISO 27001, NIST 800-53, OWASP ASVS, NIST SSDF, ISO 27017, NIST cloud guidance) plus the pre-edit and pre-commit hooks that make consultation land in code. See README.md for the product picture.

This repo uses Kiro-style spec-driven development. Read the steering docs as project memory before non-trivial work, and run feature work through the spec flow below.

Project context

  • Steering (.kiro/steering/{product,structure,tech}.md) — project-wide rules and context. Load as project memory.
  • Specs (.kiro/specs/<feature>/) — one directory per feature: spec.json, requirements.md, design.md, tasks.md, and a review.md after review.
  • Rules + templates (.kiro/settings/) — the spec engine. rules/ holds the authoring/review gates; templates/ holds the artifact skeletons.

Spec flow (human-approved gates)

Author each artifact from its template in .kiro/settings/templates/, self-check it against the matching gate in .kiro/settings/rules/, then get user approval before moving on. There are no /kiro-* slash commands in this repo — the flow is driven manually.

  1. Requirementstemplates/specs/requirements.md, gate rules/requirements-review-gate.md + rules/ears-format.md. EARS acceptance criteria, numeric IDs only.
  2. Designtemplates/specs/design.md, gate rules/design-review-gate.md + rules/design-principles.md. Boundary sections + file plan + full requirements traceability (explicit IDs, no ranges).
  3. Taskstemplates/specs/tasks.md, gate rules/tasks-generation.md + rules/tasks-parallel-analysis.md. Foundation → Core → Validation; (P) only for non-overlapping boundaries.
  4. Implementation — code to the approved design, then a review pass (e.g. parallel doc + implementation reviewers) before landing. Record outcomes in review.md.

Update spec.json phase/approvals as each gate passes. Steering edits follow rules/steering-principles.md (patterns, not file trees).

Read the full file on GitHub · 42 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. 7d ago First seen · 42 lines · 748 tokens per session scan A a7b6c2c65d56

Subscribe to this mod's changes

mcp-custos CLAUDE.md is an instructions file published in the GitHub repository an0malous/mcp-custos (3 stars, last pushed 1mo ago), licensed MIT. It adds 748 tokens to every session, about $0.0037 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.

Related

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens