Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/tripletex/mcp-dependency-version/claude-mdgit clone --depth 1 https://github.com/Tripletex/mcp-dependency-versionWrote 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/tripletex/mcp-dependency-version/claude-md)<a href="https://agentmods.dev/instructions/tripletex/mcp-dependency-version/claude-md"><img src="https://agentmods.dev/badge/instructions/tripletex/mcp-dependency-version/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 | $0.00762 | $0.00762 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
mcp-dependency-version 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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project guidance for Claude
Pre-push checklist
CI (.github/workflows/pr-check.yml) runs four gates and fails the PR if any
gate fails. Run all four locally before pushing — deno task check and
deno task test alone are not sufficient.
deno fmt --check # CI gate 1 — formatting
deno lint # CI gate 2 — lint
deno check main.ts # CI gate 3 — type check
deno test --allow-net --allow-read # CI gate 4 — tests
Or as a single command:
deno fmt --check && deno lint && deno check main.ts && deno test --allow-net --allow-read
Formatting (the most common failure)
deno fmt --check is strict about line breaks in import statements, type
unions, and ternaries. The Deno formatter has opinions that don't always match
what an LLM will produce on the first try. Always run deno task fmt (which
auto-fixes) after writing or editing TypeScript or Markdown files, then verify
with deno fmt --check.
If CI fails on formatting after a push, the fix is:
deno task fmt
git add -u && git commit -m "Apply deno fmt formatting"
git push
Project conventions
- Runtime: Deno v2.x. No Node.js or npm install — dependencies are declared
in
deno.jsonimportsand resolved via JSR/npm specifiers. - No emojis in code, comments, or commits unless explicitly requested.
- Commit style: plain imperative ("Add X", "Fix Y") — not conventional commits. Subject under 72 chars, explain why in the body when not obvious.
- No
Co-Authored-Bytrailer on commits unless explicitly requested.
Architecture cheat sheet
main.ts— entry point; registers all MCP tools on stdio transportsrc/registries/— one client per package registry (npm, maven, pypi, etc.)src/parsers/— one parser per dependency file formatsrc/tools/— MCP tool implementationssrc/utils/— shared utilities (cache, http, version parsing, vulnerability)src/config/— custom registry/auth configuration loader
When adding a new registry, you typically need: a registry client
(src/registries/X.ts), a parser if it has a dependency file format
(src/parsers/X.ts), and registration in src/registries/index.ts and
src/parsers/index.ts. Update the tool input enums in src/tools/*.ts and the
registry list in README.md.
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.
- 3d ago First seen · 75 lines · 762 tokens per session scan A 14f8a34d4ee8
mcp-dependency-version CLAUDE.md is an instructions file published in the GitHub repository Tripletex/mcp-dependency-version (4 stars, last pushed 1mo ago), licensed MIT. It adds 762 tokens to every session, about $0.0038 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.