Borrowing it
Nothing to install: this file belongs to LeanAndMean/scramjet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LeanAndMean/scramjet/main/CLAUDE.mdgit clone --depth 1 https://github.com/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/claude-md)<a href="https://agentmods.dev/instructions/leanandmean/scramjet/claude-md"><img src="https://agentmods.dev/badge/instructions/leanandmean/scramjet/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.
<a href="https://agentmods.dev/instructions/leanandmean/scramjet/claude-md"><img src="https://agentmods.dev/badge/instructions/leanandmean/scramjet/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.11646 | $0.11646 |
| Opus 5.5 | $0.04658 | $0.04658 |
| Sonnet 5.5 | $0.02329 | $0.02329 |
| Haiku 4.5 | $0.01165 | $0.01165 |
Grade A, and why
scramjet 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 1mo 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 — 229 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.
Repository structure
Scramjet is a product monorepo. Pi runtime packages are vendored in packages/ and modified directly where appropriate. Scramjet is not an extension of Pi — it IS the product; Pi is the runtime it uses.
scramjet/
├── packages/
│ ├── tui/ Pi runtime: terminal UI
│ ├── ai/ Pi runtime: LLM providers
│ ├── agent/ Pi runtime: agent loop, state
│ ├── coding-agent/ Pi runtime: CLI, tools, sessions
│ └── scramjet/ The product: commands, orchestration
│ ├── src/
│ ├── tests/
│ ├── bin/
│ ├── mach12/ # bundled development-methodology command set
│ ├── scramjet/ # bundled product operational command set
│ └── docs/
├── UPSTREAM_DIVERGENCE.md Tracks Pi modifications for upstream sync
├── .github/workflows/
└── package.json Root workspace config
Commands
npm run typecheck # tsgo --noEmit (all packages)
npm run build # topological build: tui -> ai -> agent -> coding-agent -> scramjet
npm test # vitest --run across all workspaces
npm run lint # biome check .
npx vitest run packages/scramjet/tests/command-status.test.ts # single test file
scramjet-command-lint --strict <command-set-root> # authoritative command-file authoring check
scramjet-command-lint is required when creating or editing Scramjet command files. Run it against each affected command-set root; resolve errors and address warnings or explain intentional legacy exceptions. If the installed/linked binary is unavailable after npm run build, use the source-tree wrapper without installing anything: node packages/scramjet/bin/scramjet-command-lint.js --strict <command-set-root>. The checker is specific to command Markdown and does not replace typecheck, tests, lint, or behavioral verification.
CI runs typecheck, build, test, lint, an npm pack round-trip smoke (including installed-runtime package-authority coverage), and a postinstall cleanup smoke on ubuntu and macOS.
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.
- 1mo ago Changed · +90 tokens per session 05dd98b916ac
- 1mo ago Changed · -7 lines · -425 tokens per session 3b01c24e214d
- 1mo ago Changed · +8 lines · +369 tokens per session 8dcc7b316967
- 1mo ago Changed · -87 tokens per session f97751f11a85
- 2mo ago Changed · +5 lines · +339 tokens per session 875014a4af44
- 2mo ago First seen · 223 lines · 11,360 tokens per session scan A e73bd16170a6
scramjet CLAUDE.md is an instructions file published in the GitHub repository LeanAndMean/scramjet (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 11,646 tokens to every session, about $0.0466 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.
scramjet CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scramjet CLAUDE.mdLeanAndMean/scramjet | Instructions file | 8 | 4d ago | Apache-2.0 | A | 11,646 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |