Borrowing it
Nothing to install: this file belongs to Dgotlieb/verdict-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.
curl -O https://raw.githubusercontent.com/Dgotlieb/verdict-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Dgotlieb/verdict-mcpWrote 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.
[](https://agentmods.dev/instructions/dgotlieb/verdict-mcp/claude-md)<a href="https://agentmods.dev/instructions/dgotlieb/verdict-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dgotlieb/verdict-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00919 | $0.00919 |
| Opus 5 | $0.00460 | $0.00460 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
verdict-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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verdict — project context for Claude Code
What this is
An MCP server giving coding agents structured, sandboxed test feedback: impact-selected pytest runs in ephemeral containers, returning compact typed verdicts (~400 tokens instead of ~40k of raw output) with stable failure fingerprints and history ("is this failure pre-existing or my regression?"). Built as an open-source credibility project for an advanced technical curriculum. Full roadmap: docs/build-plan.md. Immediate next steps: TODO-next.md.
Architecture map
src/verdict_mcp/server.py— FastMCP surface:verify,explain_failure,history,run_checkscore.py— orchestration behind the tools (import-friendly, tested directly)impact.py— grimp import-graph test selection; honest fallback to full suite withselection_noterunner/— execution backends:container.py(podman preferred, docker fallback; worktree read-only at /src, copy to /work, --network=none) andlocal.py(temp-copy fallback, never in-place)adapters/— pytest (via pytest-json-report), ruff, mypy → normalizedFailureobjectsfingerprint.py— normalized failure hashing (volatile tokens collapsed); fingerprints power historyhistory.py— SQLite (.verdict/history.db): preexisting detection, failure details, run summariesschema.py— the verdict contract;examples/demo_project/— test fixture project (one intentional failure)
Commands
uv run pytest -q # full suite (29 tests; 3 are @container and skip without a live engine)
uv run ruff check src tests # lint
On this Mac (macOS 12, x86_64) uv run/uv sync fail because cryptography>=49 (pulled in by fastmcp) ships no wheel for the platform. The lockfile is left alone for CI; locally use .venv/bin/python -m pytest -q / .venv/bin/ruff check src tests, and (re)create the env with:
uv pip install --python .venv/bin/python -e ".[dev]" anyio "cryptography<49"
Design rules (do not violate)
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.
- 8d ago First seen · 45 lines · 919 tokens per session scan A aa457697d3d4
verdict-mcp CLAUDE.md is an instructions file published in the GitHub repository Dgotlieb/verdict-mcp (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 919 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.