What is cpp-analysis-mcp CLAUDE.md?

A Claude Code instruction file for the cpp-analysis-mcp repository. It records the maintainer's required workflow, architecture documents, source-control rules, and development habits.

Guiding repository work such as reviewing architecture, checking branches, following git-flow, and preparing conventional commits without merging pull requests.

It gives coding sessions a consistent set of repository rules, including which documents to read, how to use branches, and how commits and pull requests should be handled.

How GusDawn123/cpp-analysis-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to GusDawn123/cpp-analysis-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/GusDawn123/cpp-analysis-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/GusDawn123/cpp-analysis-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/gusdawn123/cpp-analysis-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gusdawn123/cpp-analysis-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gusdawn123/cpp-analysis-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gusdawn123/cpp-analysis-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/gusdawn123/cpp-analysis-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gusdawn123/cpp-analysis-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,599 This file is loaded in full into every session.

When invoked 1,599 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	$0.01599	$0.01599
Opus 5.5	$0.00640	$0.00640
Sonnet 5.5	$0.00320	$0.00320
Haiku 4.5	$0.00160	$0.00160

Measured 2mo ago against content hash f78521a8db39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cpp-analysis-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 2mo 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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — how this repo is worked

Instructions for Claude (any machine, any session). These encode the maintainer's standing decisions; they override default behavior. When they conflict with something newer the maintainer says, the maintainer wins — then update this file.

Read first, always

docs/getting-started.md — the contributing workflow lives at the bottom. It was missed once; it is never missed again.
git branch -r before assuming anything about branches. This repo had in-flight feature branches a session once ignored.
docs/architecture.md (v1 layers, four rules) and docs/architecture-v2.md (five-layer target: surface / planner / analyzers / store / engines).
ADRs in docs/adr/ are binding decisions, each with its precedents.

Source control (non-negotiable)

git-flow: feat/... branches fork from develop, PRs target develop, green CI required. main only receives merges from develop at release.
Never merge a PR. The maintainer merges, or delegates explicitly per-PR.
One branch per chunk, one conventional commit per sub-chunk.
Commit/PR titles: type(scope): imperative summary (feat, fix, docs, refactor, chore, test). Never internal plan vocabulary ("Phase 1", "Chunk 1.2") in titles — plan words live in specs and milestones, not git history.

The working ritual (per sub-chunk, six steps, no skipping)

Plan — goal, files touched, interface changes, test plan, performance notes (data structures with complexity stated), risks and judgment calls.
Refine — the maintainer tears it up; nothing is written before their blessing.
Implement — tests first, code second, in the repo's voice (see "Comments & docs" below; comments say why; match what surrounds you).
- 3.5 Self-review — a deliberate pass for simplicity, naming, dead weight, idiom-match, before any external review.
Review — CodeRabbit CLI on exactly that diff (coderabbit review --agent -t uncommitted). Code diffs only — never run it on docs-only changes.
Fix — verify every finding against the code before acting; accept what is real, reject with a recorded reason (docstring, test, or commit message) what is not. Findings are data, not orders.
Commit — one conventional commit whose message tells the story, including design corrections and rejected-finding reasons.

Read the full file on GitHub · 122 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.

2mo ago First seen · 122 lines · 1,599 tokens per session scan A f78521a8db39

Subscribe to this mod's changes

cpp-analysis-mcp CLAUDE.md is an instructions file published in the GitHub repository GusDawn123/cpp-analysis-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,599 tokens to every session, about $0.0064 per session on Opus 5.5. 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.

C and C++Planning ai-agents clang developer-tools mcp-server profiling

cpp-analysis-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cpp-analysis-mcp CLAUDE.mdGusDawn123/cpp-analysis-mcp	Instructions file	0	2mo ago	MIT	A	1,599	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

cpp-analysis-mcp: Instructions file for Claude Code