Borrowing it
Nothing to install: this file belongs to tiago-peixoto/claude-shapeup. 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/tiago-peixoto/claude-shapeup/main/CLAUDE.mdgit clone --depth 1 https://github.com/tiago-peixoto/claude-shapeupWrote 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/tiago-peixoto/claude-shapeup/claude-md)<a href="https://agentmods.dev/instructions/tiago-peixoto/claude-shapeup/claude-md"><img src="https://agentmods.dev/badge/instructions/tiago-peixoto/claude-shapeup/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/tiago-peixoto/claude-shapeup/claude-md"><img src="https://agentmods.dev/badge/instructions/tiago-peixoto/claude-shapeup/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 | $0.01296 | $0.01296 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
claude-shapeup 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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo (baseline instructions for any Claude agent)
This repo is a Claude Code plugin. Its skills under skills/*/SKILL.md are
mostly prompts — the agent's behavior is defined by the text, not by code.
A prompt edit can silently shift what the agent produces, even when every
deterministic test still passes. Full rationale:
CONTRIBUTING.md.
One-time setup (per clone)
Run once after cloning, to activate the local git hooks that enforce the workflow at commit and push time:
bash scripts/setup-hooks.sh
This points core.hooksPath at .githooks/ (tracked in the repo), so
the hooks stay in sync as the repo evolves.
Test architecture (two layers, no snapshots)
| Layer | Subject | Determinism | Where it fires |
|---|---|---|---|
| Unit | Hooks, scripts, prompt structure (placeholder grounding, $FEATURE_DIR block locality, hook wiring) |
Deterministic — exact text assertions | tests/unit/*.sh; runs on pre-commit |
| Behavioral | Agent outcomes via LLM-as-judge against rubric-based scenarios | Non-deterministic — evaluated by meaning, not text | tests/behavioral/; runs on pre-push when prompts / hooks / references change |
There is no snapshot/baseline layer. Exact-text diffs against a non-deterministic generator are a category error. Regressions on meaning belong in the behavioral layer; regressions on scaffolding belong in the unit layer.
Before editing a prompt
Use the behavior-tdd skill (.claude/skills/behavior-tdd/) for any change to agent
behavior — editing a skills/*/SKILL.md, a references/* doc, or a behavioral contract. It
operationalizes the steps below: establish the behavioral RED, prove it with the ablation
negative-control (run-behavioral.sh --ablate), edit, verify GREEN pass^k + unit + regression,
and commit cleanly with a single version bump. Don't hand-roll prompt edits without it.
- Start from a concrete signal: a failing test, a user complaint, or a behavioral scenario. No speculative rewording — if you can't describe what's broken, don't edit.
- Run
bash tests/run-all.sh --unit. Must be green before continuing. - Dispatch an Explore subagent to audit the current state of the skill you plan to edit. Do not edit blind.
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.
- 9d ago First seen · 115 lines · 1,296 tokens per session scan A ed0e0d760e68
claude-shapeup CLAUDE.md is an instructions file published in the GitHub repository tiago-peixoto/claude-shapeup (22 stars, last pushed 2mo ago), licensed MIT. It adds 1,296 tokens to every session, about $0.0065 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.