Borrowing it
Nothing to install: this file belongs to baek-labs/hames. 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/baek-labs/hames/main/CLAUDE.mdgit clone --depth 1 https://github.com/baek-labs/hamesWrote 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/baek-labs/hames/claude-md)<a href="https://agentmods.dev/instructions/baek-labs/hames/claude-md"><img src="https://agentmods.dev/badge/instructions/baek-labs/hames/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/baek-labs/hames/claude-md"><img src="https://agentmods.dev/badge/instructions/baek-labs/hames/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 | $0.00267 | $0.00267 |
| Opus 5.5 | $0.00107 | $0.00107 |
| Sonnet 5.5 | $0.00053 | $0.00053 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
hames 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 28d 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.
What it actually says
Hames plugin development
src/ is the source of truth. The packages/codex and packages/claude trees are generated distribution outputs; rebuild them with node scripts/build.mjs and never maintain host copies by hand.
The Core product surface is /setup, /ready, /go, /index, and /doctor. Preserve existing project entry files during setup. A same-session /go approves and activates only the exact contract just presented; critical actions still require separate confirmation. Store only safe evidence metadata.
All project locations are relative to the configured project root. File hooks must reject lexical and symlink escape, while descriptions must state that shell and unstructured UI enforcement is best-effort.
For changes, add or update tests first, then run:
node --test
node scripts/build.mjs
node scripts/verify.mjs
git diff --check
Do not commit, push, release, publish, or submit a marketplace listing without an explicit request.
Hames includes adapted DryForge intent and execution workflows. Ordinary work requires no Git, and Git mutations require an explicit user request. Workspace roles are user-defined; long-lived docs are shared at the chosen root and loaded selectively. Index auditing is read-only; observed file changes update managed index blocks.
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.
- 28d ago Changed · +2 lines · +61 tokens per session 666ffb74474f
- 1mo ago Changed · +7 tokens per session d0fed13a3f42
- 1mo ago Changed · -124 lines · -939 tokens per session ff8c702298b2
- 1mo ago First seen · 143 lines · 1,138 tokens per session scan A f9515cc1e7a4
hames CLAUDE.md is an instructions file published in the GitHub repository baek-labs/hames (5 stars, last pushed 28d ago), licensed MIT. It adds 267 tokens to every session, about $0.0011 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.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.