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/hitmandark07/neatcodeai/claude-mdgit clone --depth 1 https://github.com/HITMANdark07/neatcodeaiWhat 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 | $0.02125 | $0.02125 |
| Opus 5 | $0.01063 | $0.01063 |
| Sonnet 5 | $0.00425 | $0.00425 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
neatcodeai 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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repository.
Repository Status
Monorepo scaffolded (pnpm workspaces + TypeScript + tsup + Vitest). Three packages under packages/:
@neatcodeai/core— parser, graph, sync, query (consumed by cli + mcp)@neatcodeai/cli— binaryneatcode(ESM, shebang via tsup banner)@neatcodeai/mcp— MCP stdio serverneatcode-mcp(11 tools wired)
Working end-to-end: neatcode init + neatcode sync + neatcode ask against a TS repo (ts-morph parser → SQLite graph at .neatcode/graph.db), with file-hash cache, .neatcodeignore honoring, batched transactions, and confidence labels on nodes/edges. MCP server exposes 11 tools over stdio (query_graph, find_node, trace_flow, validate_diff, get_rules, propose_rule_from_prompt, accept_proposed_rule, derive_candidates, accept_derived_candidates, get_repo_overview, add_note). Test suite via pnpm test (vitest).
The PRD (repo-brain-prd-v0.2.md) is the spec; the locked v0.1 design lives in Claude memory (project_v01_design.md) and supersedes any conflicting line in this file.
Build / Test / Run
pnpm install # one-time setup (auto-builds better-sqlite3 native module)
pnpm build # build all three packages
pnpm typecheck # tsc --noEmit across packages
pnpm test # vitest run (root config)
pnpm test:watch # vitest watch
pnpm clean # remove dist/ from each package
# Smoke-test the CLI after build
node packages/cli/dist/index.js --help
@neatcodeai/core re-exports from ./dist/index.js (ESM, dts emitted). @neatcodeai/mcp depends on it via workspace:*. @neatcodeai/cli depends on both core and mcp (so npm i -g @neatcodeai/cli puts neatcode and neatcode-mcp on PATH in one shot — added in v0.1.1).
MCP server: wiring to Claude Code
The repo ships an .mcp.json at the root that points Claude Code at the locally-built neatcode-mcp binary (absolute path). When you open Claude Code in this repo, it reads .mcp.json and starts the server.
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.
- yesterday First seen · 104 lines · 2,125 tokens per session scan A 6aa2d78571fb
neatcodeai CLAUDE.md is an instructions file published in the GitHub repository HITMANdark07/neatcodeai (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,125 tokens to every session, about $0.0106 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
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.
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).
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.