TechDebtMCP: Instructions file for Claude Code

CLAUDE.md

TechDebtMCP CLAUDE.md is an instructions file for Claude Code from PierreJanineh/TechDebtMCP. It costs 5,794 tokens per session, scanned A, original, MIT.

Project instructions for TechDebtMCP, including its required installation, type-checking, linting, testing, and build commands. Technical debt is the future maintenance work created by shortcuts or unresolved problems in software.

In plain words
What is it for?
Use them when contributing to TechDebtMCP, reviewing pull requests, running its quality checks, building the MCP bundle, or following the project's rules for handling missing or failing stages.
Why use it?
They provide the repository's source of truth for development checks and explain what agents should do when a command is unavailable or fails.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is PierreJanineh/TechDebtMCP's own configuration. It tells Claude Code how to work on TechDebtMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TechDebtMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PierreJanineh/TechDebtMCP. 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/PierreJanineh/TechDebtMCP/develop/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/PierreJanineh/TechDebtMCP

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.

agentmods badge for TechDebtMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pierrejanineh/techdebtmcp/claude-md.svg)](https://agentmods.dev/instructions/pierrejanineh/techdebtmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pierrejanineh/techdebtmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pierrejanineh/techdebtmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,794 This file is loaded in full into every session.
When invoked 5,794 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05794 $0.05794
Opus 5 $0.02897 $0.02897
Sonnet 5 $0.01159 $0.01159
Haiku 4.5 $0.00579 $0.00579

Measured 6d ago against content hash ff15aa4872c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

TechDebtMCP 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 · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 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.

Build & Test Commands

For agents and contributors — run these from the repo root. The agent that processes PR review threads (pr-automation/pr-reviewer) consults this section before pushing, so keep it accurate.

Stage Command
Install (CI) npm ci --ignore-scripts
Install (dev) npm install --include=dev --ignore-scripts
Typecheck npm run typecheck
Lint npm run lint
Test npm test
Build npm run build

Rules for agents:

  • These commands are the source of truth. If a stage is N/A, skip it entirely — do not search for alternatives, do not run binaries directly (node_modules/.bin/jest), do not install missing tools, do not modify package.json to add scripts.
  • If a listed command fails, fix the underlying issue or report it. Do not "work around" by switching to a different command.
  • If you believe a stage should exist but doesn't, surface that as a finding in your PR summary — do not silently add it.
  • Install context matters. Both install commands pass --ignore-scripts because package.json declares "prepare": "npm run build" — leaving the hook enabled causes every install to run tsc, which duplicates the later Build step and wastes CI minutes. In CI, npm ci --ignore-scripts fails fast on lockfile drift while skipping the double-compile. Locally, npm install --include=dev --ignore-scripts additionally pulls the devDependencies that an agent needs for npm run lint / npm test.

Lint config lives in eslint.config.mjs (flat config, ESLint 10 + typescript-eslint 8). Tests and build scripts are ignored by lint; only src/**/*.ts is checked.

Read the full file on GitHub · 304 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.

  1. 6d ago First seen · 304 lines · 5,794 tokens per session scan A ff15aa4872c6

Subscribe to this mod's changes

TechDebtMCP CLAUDE.md is an instructions file published in the GitHub repository PierreJanineh/TechDebtMCP (7 stars, last pushed 1mo ago), licensed MIT. It adds 5,794 tokens to every session, about $0.0290 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.