What is dependency-fitness-mcp CLAUDE.md?

A project instruction file for dependency-fitness-mcp, an MCP server that checks npm dependency health and verifies possible replacements. It records the project’s design rules, commands, layout, and known build details.

Use it when changing dependency-fitness-mcp to preserve its migration-target checks, validation across npm and security sources, confidence reporting, and required project workflows.

It keeps development focused on the important guarantee: recommendations must be cross-checked and must not invent a replacement when no safe successor is verified.

How TweedBeetle/dependency-fitness-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TweedBeetle/dependency-fitness-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/TweedBeetle/dependency-fitness-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/TweedBeetle/dependency-fitness-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/tweedbeetle/dependency-fitness-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tweedbeetle/dependency-fitness-mcp/claude-md)

Your own site

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

Per session 862 This file is loaded in full into every session.

When invoked 862 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.

Model	Per session	Once invoked
Fable 5.1	$0.00862	$0.00862
Opus 5	$0.00431	$0.00431
Sonnet 5	$0.00172	$0.00172
Haiku 4.5	$0.00086	$0.00086

Measured 10d ago against content hash 4ab30d5cade8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dependency-fitness-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 10d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dependency-fitness-mcp — project memory

The "fast-validate" bet from the revenue-paths sequenced portfolio: an MCP server that returns a cross-validated npm dependency fitness verdict with an inferred + verified safe migration target. Origin brief: ~/projects/revenue-paths/evidence/dossier/package-version-mcp.md. User-facing overview: README.md. Validation design + kill criterion: KILL_CRITERION.md. Directory-seeding playbook (listing copy + per-directory steps): SEEDING.md.

The product invariant (the moat — don't erode it)

The value is NOT "is it deprecated" (deps.dev serves that free). It is:

migration-target inference — parse the maintainer's deprecation notice for a successor, then verify that successor exists and isn't itself deprecated before recommending it; and
cross-validation across npm + deps.dev + OSV + GitHub with an explicit confidence level. Never guess a migration target — deprecated-with-no-clean- successor must return low confidence + "manual evaluation required", not a plausible-but-wrong package. The adversarial case the parser must keep passing: request-promise names request as the reason it's deprecated, NOT a target.

Commands

npm run build   # tsc -> dist/  (noEmitOnError; shebang in src/index.ts is preserved by tsc)
npm test        # vitest, offline/deterministic — the synthesis logic (parser, cross-val, migration)
npm run smoke   # live: hits real npm/deps.dev/OSV/GitHub, prints verdicts for representative pkgs
npm run dev     # run the stdio server from source
npx tsx scripts/mcp-client-test.ts   # e2e: drives the built server as a real MCP client

Layout

src/sources/{npm,depsdev,osv,github}.ts — one client per data source. npm is authoritative (may throw on hard failure); the other three are best-effort corroborators (a failure lowers confidence + adds a warning, never fabricates).
src/verdict.ts — the synthesis. Pure, unit-tested helpers (parseMigrationHint, crossValidateDeprecation, selectMigrationTarget, computeSuperseded, computeConfidence) + the getVerdict orchestrator (source clients injectable via VerdictDeps for deterministic tests).
src/audit.ts — batch / package.json parsing (CI tier). src/render.ts — human-readable mirror of the verdict. src/index.ts — MCP server (2 tools).
src/types.ts — zod schemas; Verdict is the contract.

Read the full file on GitHub · 64 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.

10d ago First seen · 64 lines · 862 tokens per session scan A 4ab30d5cade8

Subscribe to this mod's changes

dependency-fitness-mcp CLAUDE.md is an instructions file published in the GitHub repository TweedBeetle/dependency-fitness-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 862 tokens to every session, about $0.0043 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.

ai-agents dependencies mcp mcp-server model-context-protocol npm

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 · 5,153 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

dependency-fitness-mcp: Instructions file for Claude Code