Borrowing it
Nothing to install: this file belongs to statecrafting/spec-spine. 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/statecrafting/spec-spine/main/CLAUDE.mdgit clone --depth 1 https://github.com/statecrafting/spec-spineWrote 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/statecrafting/spec-spine/claude-md)<a href="https://agentmods.dev/instructions/statecrafting/spec-spine/claude-md"><img src="https://agentmods.dev/badge/instructions/statecrafting/spec-spine/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/statecrafting/spec-spine/claude-md"><img src="https://agentmods.dev/badge/instructions/statecrafting/spec-spine/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 | $0.04741 | $0.04741 |
| Opus 5.5 | $0.01896 | $0.01896 |
| Sonnet 5.5 | $0.00948 | $0.00948 |
| Haiku 4.5 | $0.00474 | $0.00474 |
Grade A, and why
spec-spine 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 — 315 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.
What this is
spec-spine turns a markdown spec corpus into a typed, hash-verifiable authority ledger and refuses code that drifts from its owning spec at PR time. It is a three-crate Rust workspace publishing an installable library + CLI, plus npm and PyPI shims that ship the prebuilt binary.
Two documents outrank this one for their subjects. Read
docs/design/00-architecture.md for the design (crate layout, full Config,
public API, exit codes, schema plan, and the provenance of every ported
algorithm). Read AGENTS.md for how work is actually done here: it is the
cross-agent authority (Claude Code, Codex CLI, Cursor, Copilot, via the
AGENTS.md standard), it holds the session protocol /prime executes, and its
"Working the backlog" section is the operating loop. The gate chain is
defined there, not here, and harness_skills.rs asserts every skill's inlined
gate floor is a subset of that list, so a step added to AGENTS.md reaches
every skill. The executable form is Statecraft's managed
scripts/statecraft/gate.sh; the root Makefile is a developer compatibility
interface (spec 094 as amended by spec 156). .claude/ itself is spec 093's.
Commands
The toolchain is pinned in rust-toolchain.toml (channel 1.92.0); MSRV is
1.90 / edition 2024 (spec 135: the floor the locked tree needs; CI builds and tests there). Always pass --locked; CI does, and the committed
Cargo.lock is part of the determinism contract (tree-sitter grammars are
pinned exact).
cargo build --workspace --locked
cargo test --workspace --locked
cargo clippy --workspace --all-targets --locked -- -D warnings
cargo fmt --all --check
# A single test / one test file:
cargo test -p spec-spine-core --test couple # one integration test file
cargo test -p spec-spine-core compile:: # tests matching a path
cargo test --workspace emitted_registry_conforms # one test by name
# tree-sitter sits behind the default-on `symbol-resolution` feature (spec 025).
# CI builds and tests without it, and asserts the grammars are absent:
cargo test -p spec-spine-core --no-default-features --locked
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 · +1 lines · +7 tokens per session f74ceb8c569a
- 1mo ago Changed · +4 lines · +105 tokens per session 4eeae3ba7941
- 1mo ago Changed · +5 lines · +65 tokens per session b95fdda5976b
- 1mo ago Changed · +33 lines · +512 tokens per session d6b5c8e10251
- 1mo ago Changed · +5 lines · +109 tokens per session 020894382a0c
- 1mo ago Changed · +104 lines · +1,525 tokens per session 7b38ef09f758
- 2mo ago First seen · 163 lines · 2,418 tokens per session scan A 41a92f1bf949
spec-spine CLAUDE.md is an instructions file published in the GitHub repository statecrafting/spec-spine (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 4,741 tokens to every session, about $0.0190 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 2026-09-07.
spec-spine CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spec-spine CLAUDE.mdstatecrafting/spec-spine | Instructions file | 11 | 8d ago | Apache-2.0 | A | 4,741 | 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 |