What is modelrisk-mcp CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, when working on the modelrisk-mcp project. They define work preferences, commit checks, version changes, pushing code, and the automated release process.

Working on, committing, and releasing changes in the modelrisk-mcp repository.

They give the coding assistant project-specific rules, reducing mistakes around quality checks, commits, versioning, and releases.

How vosesoftware/modelrisk-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vosesoftware/modelrisk-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/vosesoftware/modelrisk-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vosesoftware/modelrisk-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/vosesoftware/modelrisk-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/vosesoftware/modelrisk-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vosesoftware/modelrisk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vosesoftware/modelrisk-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vosesoftware/modelrisk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vosesoftware/modelrisk-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,195 This file is loaded in full into every session.

When invoked 1,195 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01195	$0.01195
Opus 5.5	$0.00478	$0.00478
Sonnet 5.5	$0.00239	$0.00239
Haiku 4.5	$0.00120	$0.00120

Measured 1mo ago against content hash 050e7c65c9cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

modelrisk-mcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

After a tag pushes, watch the run with `gh run watch <id> --exit-status` and confirm all five jobs green. Then confirm the version appears on PyPI (`curl pypi.org/pypi/modelrisk-mcp/json | jq .info.version`) and on the M

CLAUDE.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working preferences for Claude on this repo

Read this before doing work on modelrisk-mcp.

Git push policy

Always do git push yourself. Don't ask the user to switch to PowerShell and run it. The credential dialog works reliably from the bash/PowerShell shell Claude uses, provided the repo-local credential helper is set to manager:

git config --local credential.https://github.com.helper "manager"

That's already configured for modelrisk-mcp and shouldn't need to be re-set. If a push hangs, it's almost always Git Credential Manager waiting on the OS chooser — wait it out or check the user's screen for the dialog. Don't fall back to telling the user to push manually.

The standard sequence after a tagged commit:

git push origin main
git push origin <new-tag>
gh run watch <run-id> --repo vosesoftware/modelrisk-mcp --exit-status

Release pipeline (automated)

Pushing a tag v*.*.* or v*.*.*-* triggers .github/workflows/release.yml. Five jobs run, all green-or-fail:

build-wheel — wheel + sdist via uv build
build-windows-exe — PyInstaller exe + obfuscation scan (release-blocker)
publish-pypi — wheel + sdist via OIDC trusted publishing
publish-mcp-registry — mcp-publisher via GitHub OIDC against registry.modelcontextprotocol.io
github-release — assets attached to a GitHub Release page

After a tag pushes, watch the run with gh run watch <id> --exit-status and confirm all five jobs green. Then confirm the version appears on PyPI (curl pypi.org/pypi/modelrisk-mcp/json | jq .info.version) and on the MCP Registry.

Quality gate before every commit

Always run all three before committing. No exceptions:

.venv/Scripts/python.exe -m pytest tests/unit -q
.venv/Scripts/python.exe -m ruff check src tests scripts
.venv/Scripts/python.exe -m mypy src

mypy runs on src only — running it on tests/ surfaces a lot of test-time-only type: ignore lint noise that's not actionable.

Version bumping

Read the full file on GitHub · 75 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.

1mo ago Changed · +118 tokens per session 050e7c65c9cb
2mo ago First seen · 75 lines · 1,077 tokens per session scan A d41f33503d66

Subscribe to this mod's changes

modelrisk-mcp CLAUDE.md is an instructions file published in the GitHub repository vosesoftware/modelrisk-mcp (0 stars, last pushed 24d ago), licensed MIT. It adds 1,195 tokens to every session, about $0.0048 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

modelrisk-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
modelrisk-mcp CLAUDE.mdvosesoftware/modelrisk-mcp	Instructions file	0	24d ago	MIT	A	1,195	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

modelrisk-mcp: Instructions file for Claude Code