Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/commerce-atoms/agents/claude-mdgit clone --depth 1 https://github.com/commerce-atoms/agentsWrote 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/commerce-atoms/agents/claude-md)<a href="https://agentmods.dev/instructions/commerce-atoms/agents/claude-md"><img src="https://agentmods.dev/badge/instructions/commerce-atoms/agents/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 | $0.00514 | $0.00514 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
agents 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 4d 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
CLAUDE.md — @commerce-atoms/agents (kit authoring)
You are working on the npm package itself, not a Hydrogen storefront. Read AGENTS.md and then CONTRIBUTING.md before doing anything else.
The shipped product lives under kit/ and has its own kit/CLAUDE.md — those rules are for AI agents in storefront repos and do not govern this repo.
Behavioural defaults for this repo
- Edit, don't speculate. When asked to change behaviour in
src/orbin/, read the file first, then propose a minimal diff. The validators are pure; new tests should accompany behaviour changes. - TypeScript strict mode is non-negotiable. Don't suppress type errors with
as any,// @ts-expect-error, or// @ts-ignore. Fix the root cause. - Run
npm run verifyafter substantive edits. It runstsc --noEmit, the INDEX.json linter, and the test suite. If something fails, fix before reporting work as done. - Don't edit content under
kit/without readingkit/AGENTS.mdfirst. Treat that subtree as a separate sub-project. - Releases happen via tag + CI, not from a workstation. If asked to publish, push a tag; do not invoke
npm publishdirectly.
Where to look
| Question | Answer lives in |
|---|---|
| How is content shipped to consumers? | src/sync.ts + bin/sync.ts |
| How is a new store initialised? | src/init.ts |
| How are architecture rules enforced in consumer repos? | src/validate.ts + src/internal/validators/ |
| What lives in the kit? | kit/INDEX.json |
| Why a decision was made? | kit/docs/decisions/ |
| How do I add a rule / skill / command / prompt / persona? | CONTRIBUTING.md → "Kit content" |
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.
- 4d ago First seen · 25 lines · 514 tokens per session scan A 115ef19d7773
agents CLAUDE.md is an instructions file published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 514 tokens to every session, about $0.0026 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
syncai copilot-instructions.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.
syncai AGENTS.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.
syncai CLAUDE.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
agentforge CLAUDE.md
Instructions for mrzroot/agentforge, covering claude.md - project directives for claude code, project overview: agentforge, commands & environment, code architecture & philosophy and architectural conventions.