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/pierrejanineh/techdebtmcp/copilot-instructionsgit clone --depth 1 https://github.com/PierreJanineh/TechDebtMCPWrote 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/pierrejanineh/techdebtmcp/copilot-instructions)<a href="https://agentmods.dev/instructions/pierrejanineh/techdebtmcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/pierrejanineh/techdebtmcp/copilot-instructions.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 | $0.02890 | $0.02890 |
| Opus 5 | $0.01445 | $0.01445 |
| Sonnet 5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
TechDebtMCP copilot-instructions.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 4d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions for Tech Debt MCP
See CLAUDE.md for coding standards, architecture, conventions, and recipes. This file covers Copilot-specific workflows only.
Project Overview
Tech Debt MCP is a Model Context Protocol server for analyzing technical debt across 14 programming languages. It integrates with GitHub Copilot and other MCP-compatible clients.
Architecture
src/
├── index.ts # Thin entry point — delegates to src/server/
├── types/index.ts # All TypeScript interfaces (single source of truth)
├── config/languages.ts # Language configurations (extensible)
├── core/
│ ├── analysisEngine.ts # Main orchestrator
│ ├── sqaleEngine.ts # SQALE metrics
│ └── customRulesEngine.ts # Custom rules engine
├── server/
│ ├── setup.ts # Server creation, version resolution, stdio transport
│ ├── handlers.ts # Tool call dispatch (delegates to domain handlers)
│ ├── tools.ts # Centralized TOOL_DEFINITIONS array
│ ├── inputParser.ts # Tool argument validation (requireString, optionalString, etc.)
│ ├── argValidation.ts # Argument coercion and constraint checks
│ ├── resourceHandlers.ts # MCP resource templates (debt://summary, debt://issues)
│ ├── formatters.ts # Report formatting helpers
│ ├── configValidator.ts # Config validation handler
│ ├── customRulesHandlers.ts # Custom rules CRUD & execution handlers
│ └── dependencyHandlers.ts # Dependency analysis handlers
├── analyzers/
│ ├── baseAnalyzer.ts # Abstract base class (shared logic)
│ ├── index.ts # Factory: createAnalyzer()
│ ├── [language]Analyzer.ts # One file per language (14 total)
│ ├── swiftUiChecks.ts # SwiftUI Phase 1 checks
│ ├── swiftUiChecksPhase2.ts # SwiftUI Phase 2 checks
│ └── dependencies/ # 10 ecosystem parsers + factory
└── utils/fileUtils.ts # File system helpers
Copilot PR Review Workflow
Before Creating a PR
- Run
npm test— all tests must pass - Run
npm run build— no TypeScript errors - Update relevant docs (README.md, ROADMAP.md, CHANGELOG.md, CLAUDE.md, ARCHITECTURE.md,
.github/copilot-instructions.md) — see Doc Files to Check for the full list
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.
- 4d ago First seen · 151 lines · 2,890 tokens per session scan A 38d1b49a2213
TechDebtMCP copilot-instructions.md is an instructions file published in the GitHub repository PierreJanineh/TechDebtMCP (7 stars, last pushed 1mo ago), licensed MIT. It adds 2,890 tokens to every session, about $0.0145 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
agi-in-md CLAUDE.md
Instructions for Cranot/agi-in-md, covering agi in md, the compression taxonomy, key results, foundation (rounds 1-24) and levels 8-13 (rounds 25-26).
mcp-codebase AGENTS.md
AGENTS.md instructions for DmitriyOT/mcp-codebase, covering agents.md, documentation workflow (required), project overview, tech stack and requirements and build and run commands.
claude-tap AGENTS.md
Instructions for liaohch3/claude-tap, covering maintainer automation notes, agents 索引, documentation boundary, review guidelines and pre-commit hook.
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
opencodex AGENTS.md
AGENTS.md instructions for lidge-jun/opencodex, covering agents.md, what this project is, repository layout, optional subsystems stay off the core path and the devlog directory.
goai AGENTS.md
AGENTS.md instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.