What is armis-appsec-mcp CLAUDE.md?

A Claude Code plugin that scans source code for security problems and can check code changes before they are committed or submitted for review. It provides scans through an MCP server, automatic checks, and a /security-scan command.

Use it to scan files, code, or changes; approve findings; inspect scan settings; and enforce security checks around Git commits, pushes, and pull requests.

It helps catch security issues before code is committed, pushed, or proposed in a pull request, reducing the chance that unsafe code reaches the project.

How ArmisSecurity/armis-appsec-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ArmisSecurity/armis-appsec-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/ArmisSecurity/armis-appsec-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ArmisSecurity/armis-appsec-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/armissecurity/armis-appsec-mcp/claude-md.svg)](https://agentmods.dev/instructions/armissecurity/armis-appsec-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/armissecurity/armis-appsec-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/armissecurity/armis-appsec-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,904 This file is loaded in full into every session.

When invoked 4,904 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.04904	$0.04904
Opus 5	$0.02452	$0.02452
Sonnet 5	$0.00981	$0.00981
Haiku 4.5	$0.00490	$0.00490

Measured 6d ago against content hash e92866056119, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

armis-appsec-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 6d 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 · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

A Claude Code plugin (not a library) that exposes Armis's AI-powered SAST scanner through three surfaces:

MCP server (server.py) — tools scan_code, scan_file, scan_diff, approve_findings, debug_config and the appsec://last-scan resource.
PreToolUse hooks (hooks/) — a commit gate that blocks git commit / git push / gh pr create until a scan has passed, plus a guard that prevents Write/Edit from forging .scan-pass.
Slash command (skills/security-scan/SKILL.md) — on-demand /security-scan invocation.

Distribution is via .claude-plugin/marketplace.json; the plugin installs under ~/.claude/plugins/cache/armis-appsec-mcp/armis-appsec/<version>/ and is launched by run.sh (which bootstraps a per-install .venv keyed off requirements.txt's SHA-256).

Requires Python 3.12+. Credentials (ARMIS_CLIENT_ID, ARMIS_CLIENT_SECRET) live in a .env in the plugin directory.

Common commands

make lint          # ruff check . --fix
make format        # ruff format .
make format-check  # ruff format --check .  (what CI runs)
make typecheck     # mypy . --exclude '.venv|__pycache__|hooks/tests'
make test          # pytest --cov --cov-report=term-missing
make check         # format-check + lint + typecheck + test  (full CI gate locally)

# Run a single test file / test
pytest hooks/tests/test_suppression.py -v
pytest hooks/tests/test_server_helpers.py::test_validate_file_path_blocks_etc -v

# Other useful targets
make install-hooks   # symlink git-hooks/pre-commit into .git/hooks/
make uninstall-hooks # remove the symlink
make setup CLIENT=cursor  # generate MCP config (cursor|vscode|gemini|copilot)

# Run the MCP server directly (stdio transport, reads .env)
./run.sh
# or, if deps already installed:
python server.py

pytest.ini_options in pyproject.toml pins testpaths = ["hooks/tests"] — all tests live under hooks/tests/, even though most of them exercise server.py, scanner_core.py, auth.py, and suppression.py (not hooks). That path is historical; don't move tests trying to "fix" it.

Read the full file on GitHub · 183 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.

6d ago First seen · 183 lines · 4,904 tokens per session scan A e92866056119

Subscribe to this mod's changes

armis-appsec-mcp CLAUDE.md is an instructions file published in the GitHub repository ArmisSecurity/armis-appsec-mcp (6 stars, last pushed 25d ago), licensed Apache-2.0. It adds 4,904 tokens to every session, about $0.0245 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.

Security

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

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 · 5,182 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

armis-appsec-mcp: Instructions file for Claude Code