ism-mcp: Instructions file for Claude Code

CLAUDE.md

ism-mcp CLAUDE.md is an instructions file for Claude Code from SamuelDudley/ism-mcp. It costs 2,016 tokens per session, scanned A, original, MIT.

A repository instruction file for ism-mcp, a local MCP server that makes Australia's Information Security Manual searchable through AI tools.

In plain words
What is it for?
Use it when maintaining the server or querying security controls, comparing Information Security Manual versions, or checking coverage.
Why use it?
It tells coding agents how the project stores official security controls and version history, and how to build, test, update, and run it.

Instructions file for Claude Code

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

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/dudley/code/ism-oscal.

Reuse

Borrowing it

Nothing to install: this file belongs to SamuelDudley/ism-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/SamuelDudley/ism-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SamuelDudley/ism-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 ism-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/samueldudley/ism-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/samueldudley/ism-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,016 This file is loaded in full into every session.
When invoked 2,016 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 $0.02016 $0.02016
Opus 5.5 $0.00806 $0.00806
Sonnet 5.5 $0.00403 $0.00403
Haiku 4.5 $0.00202 $0.00202

Measured 1mo ago against content hash 354660c96f57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ism-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 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.

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 · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project guidance for AI agents

Read this before doing any work in this repo. Update it when conventions change.

What this project is

ism-mcp is a local MCP server that exposes the ASD Information Security Manual as queryable tools. It parses the official OSCAL release of the ISM (from the ACSC ism-oscal git mirror) into a version-keyed SQLite database holding the full ISM release history, then serves lookup, version-diff, and coverage tools over stdio. Read README.md for install and usage, and HANDOVER.md for current state and next planned work.

Repository layout

src/ism_mcp/         the package
  __init__.py
  __main__.py        CLI: fetch, ingest, ingest-history, update, serve, install
  models.py          vocabulary literals + response TypedDicts for the MCP tools
  store.py           version-keyed SQLite schema + queries + FTS5 + version registry
  oscal.py           parse an OSCAL ISM catalog into version metadata and control rows
  fetch.py           clone/pull the ACSC ism-oscal mirror, list tags, read files at a tag
  ingest.py          orchestrate OSCAL ingest over a directory or a git-tag walk
  diff.py            catalog delta between two versions + per-control history
  retrieve.py        cosine search + Reciprocal Rank Fusion
  embed.py           embedder protocol + fastembed and hash backends
  classification.py  classification + maturity input normalisation
  paths.py           repo-path token expansion for query enrichment
  coverage.py        coverage manifest read, validate, serialise, gaps, drift
  install.py         consumer-repo install writer
  server.py          FastMCP server: lookup, discovery, version, coverage tools
  data/              path keyword map + coverage template
tests/               pytest suite with hermetic fixtures (tests/fixtures/oscal mini catalogs)
docs/plans/              older implementation plans
docs/superpowers/plans/  implementation plans
docs/superpowers/specs/  design and vision docs
scripts/ci.sh        local CI entrypoint
.github/workflows/ci.yml  GitHub Actions: runs scripts/ci.sh and the slow suite on every trigger
pyproject.toml       uv-managed, hatchling build
glama.json           maintainer metadata for the Glama MCP directory
HANDOVER.md          session-to-session handover
README.md            user-facing install and usage

Read the full file on GitHub · 155 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. 1mo ago Changed · +29 lines · +569 tokens per session 354660c96f57
  2. 2mo ago First seen · 126 lines · 1,447 tokens per session scan A 5dd2dfe5baf1

Subscribe to this mod's changes

ism-mcp CLAUDE.md is an instructions file published in the GitHub repository SamuelDudley/ism-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,016 tokens to every session, about $0.0081 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 2026-08-31.

Related

ism-mcp CLAUDE.md compared with instructions from other repositories

ism-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ism-mcp CLAUDE.mdSamuelDudley/ism-mcpInstructions file01mo agoMITA2,016Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot