Borrowing it
Nothing to install: this file belongs to SebastianElvis/hammer. 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/SebastianElvis/hammer/main/CLAUDE.mdgit clone --depth 1 https://github.com/SebastianElvis/hammerWrote 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/sebastianelvis/hammer/claude-md)<a href="https://agentmods.dev/instructions/sebastianelvis/hammer/claude-md"><img src="https://agentmods.dev/badge/instructions/sebastianelvis/hammer/claude-md.svg" alt="Measured on agentmods" 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 | $0.02416 | $0.02416 |
| Opus 5 | $0.01208 | $0.01208 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
hammer 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 7d 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 — 99 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 repo is
hammer is a skills repo. The shipped artifact is plain markdown: agents load it on demand, there is nothing to build or lint. Currently contains one skill: teach (a tutoring skill named after Richard Hamming).
There is also a Python eval harness in evals/ (see "Evals" below). It is not part of the shipped skill — it exists to validate skill behavior against scripted scenarios. Don't import or reference evals/ from skills/.
The repo is dual-packaged:
vercel-labs/skillsformat — installable vianpx skills add SebastianElvis/hammer.- Claude Code plugin —
.claude-plugin/marketplace.jsonmakes it/plugin install-able.
Both packagings point at the same skills/teach/ directory; do not fork or duplicate content to serve them separately.
Architecture: skill vs. learner state
The hardest thing to get right in this repo is the boundary between the skill (shipped, read-only at runtime) and the learner's state (persistent, user-owned).
- Skill directory (
skills/teach/) — shipped content.SKILL.mdis the thin entrypoint;modes/*.mdare loaded on demand;references/*.mdare authoritative policy;assets/*.mdare seeds copied on first run. - Learner folder (
$TEACH_HOME, default./.teach/in the agent's cwd) — runtime state:learner.md,review.md,syllabus.md(optional, for multi-session topics),sessions/YYYY-MM-DD.md. Never inside this repo.
The skill must never write back to its own directory. Asset files are read-only seeds, copied once on first run into $TEACH_HOME. Any change to skill behavior that requires new persistent state must (a) update the asset seed and (b) leave existing learner files intact. .teach/ is gitignored as a safety net in case someone runs the skill from a clone.
Context discipline (why the skill is split the way it is)
SKILL.md is deliberately thin because everything it references costs context when loaded. Respect these rules when editing:
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.
- 7d ago First seen · 99 lines · 2,416 tokens per session scan A 25fa1561d848
hammer CLAUDE.md is an instructions file published in the GitHub repository SebastianElvis/hammer (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,416 tokens to every session, about $0.0121 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
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).
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.
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).
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.