trace-mcp: Instructions file for Claude Code

CLAUDE.md

trace-mcp CLAUDE.md is an instructions file for Claude Code from nikolai-vysotskyi/trace-mcp. It costs 5,168 tokens per session, scanned A, original, MIT.

Development instructions for trace-mcp, a code-intelligence server that indexes source code into a graph for searching, navigation, and impact analysis.

In plain words
What is it for?
Use them when developing trace-mcp or querying code relationships across its supported programming languages and frameworks.
Why use it?
They set rules for reliable technical work, including checking facts instead of inventing paths, symbols, APIs, or results.

Instructions file for Claude Code

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

This is nikolai-vysotskyi/trace-mcp's own configuration. It tells Claude Code how to work on trace-mcp 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 trace-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nikolai-vysotskyi/trace-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/nikolai-vysotskyi/trace-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-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.

agentmods badge for trace-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikolai-vysotskyi/trace-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nikolai-vysotskyi/trace-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nikolai-vysotskyi/trace-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nikolai-vysotskyi/trace-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.

agentmods 80×15 button for trace-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nikolai-vysotskyi/trace-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nikolai-vysotskyi/trace-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,168 This file is loaded in full into every session.
When invoked 5,168 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05168 $0.05168
Opus 5 $0.02584 $0.02584
Sonnet 5 $0.01034 $0.01034
Haiku 4.5 $0.00517 $0.00517

Measured 2d ago against content hash 50d72f6b5051, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

trace-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 2d 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 · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

trace-mcp Development Guide

What this project is

trace-mcp is a framework-aware code intelligence MCP server. It indexes source code into a dependency graph with full-text search, understanding 88 framework integrations across 81 languages. It exposes MCP tools for navigation, impact analysis, and framework-specific queries.

Agent Behavior — read before every task

These rules override tool routing and workflow checklists when in conflict.

No flattery, no filler

Skip openers: "Great question", "You're absolutely right", "Excellent idea", "I'd be happy to", "Absolutely!". Start the response with the answer or the action. No ceremonial closings.

Disagree when the premise is wrong

If the user's request rests on a false assumption, say so before doing the work. Agreeing with wrong premises to be polite is worse than pushback. Example: user asks to optimize a function that's not on the hot path — say that, then ask whether to proceed anyway.

Never fabricate

Not file paths, not symbol names, not API signatures, not test output, not commit hashes. If unsure, call search / get_symbol / run the command. "I don't know, let me check" beats a plausible-sounding guess.

Stop when confused

If the task has two plausible interpretations and the choice materially changes the diff, ask. Do not pick silently and proceed. Trivial/reversible tasks (typo, rename local var) — proceed.

Goal-driven execution

Rewrite vague asks into verifiable goals before writing code:

  • "Add validation" → "Write failing tests for invalid inputs (empty, malformed, oversized), make them pass."
  • "Fix the bug" → "Write a failing test reproducing the symptom, make it pass."
  • "Refactor X" → "Ensure existing test suite passes before and after, no public API changes."
  • "Make it faster" → "Benchmark current hot path, identify bottleneck with profiling, show benchmark improved."

Never report "done" based on a plausible-looking diff. Run the test/build/typecheck. Plausibility is not correctness.

Read the full file on GitHub · 320 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. 2d ago Changed 50d72f6b5051
  2. 6d ago Changed · +32 lines · +461 tokens per session 073d81d35ae6
  3. 7d ago Changed · +13 lines · +263 tokens per session 6b87302a5172
  4. 8d ago Changed · +15 tokens per session 42fd7421f8f6
  5. 12d ago First seen · 275 lines · 4,429 tokens per session scan A 58e08f688ca3

Subscribe to this mod's changes

trace-mcp CLAUDE.md is an instructions file published in the GitHub repository nikolai-vysotskyi/trace-mcp (175 stars, last pushed today), licensed MIT. It adds 5,168 tokens to every session, about $0.0258 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 2026-08-30.

Related

Other instructions, from other repositories

repobrain copilot-instructions.md

Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.

study8677/repobrain · 229 tokens

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.

github/spec-kit · 7,126 tokens

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

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.

langchain-ai/langchain · 4,469 tokens