Borrowing it
Nothing to install: this file belongs to Gusto/baerly-storage. 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/Gusto/baerly-storage/main/CLAUDE.mdgit clone --depth 1 https://github.com/Gusto/baerly-storageWrote 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/gusto/baerly-storage/claude-md)<a href="https://agentmods.dev/instructions/gusto/baerly-storage/claude-md"><img src="https://agentmods.dev/badge/instructions/gusto/baerly-storage/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/gusto/baerly-storage/claude-md"><img src="https://agentmods.dev/badge/instructions/gusto/baerly-storage/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 | $0.06922 | $0.06922 |
| Opus 5.5 | $0.02769 | $0.02769 |
| Sonnet 5.5 | $0.01384 | $0.01384 |
| Haiku 4.5 | $0.00692 | $0.00692 |
Grade A, and why
baerly-storage 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 — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for AI coding agents working in this repo. Keep this file lean — only content that cannot be inferred from the code belongs here.
What this is
baerly-storage is a vendorless document database that runs over
any S3-compatible storage API. The data lives in your bucket; the
protocol kernel is small enough that an LLM can use the public API
zero-shot from the .d.ts files alone. Theoretical foundations live
in docs/.
Current state: Open source under Apache-2.0, published publicly as
@gusto/baerly-storage (and the @gusto/create-baerly-storage
scaffolder) on npm (npmjs.com) with publishConfig.access: "public".
See
docs/contributing/publishing.md for
the publish workflow.
The protocol kernel and HTTP server are landed. Day-1 templates ship for Cloudflare Workers and self-hosted Node; both are first-class. AWS Lambda / Bun / Deno / Fly are an adapter package away.
Toolchain
Read packageManager + devDependencies in package.json. Don't
introduce alternate tooling without justification.
Verification
Under Claude Code, vitest runs use the compact minimal reporter —
vitest 4.1 auto-detects AI-agent environments, and the repo config
(vitest.config.ts) additionally pins this behavior when
CLAUDECODE=1 is set so it isn't silently broken by detection
changes. Failures still print in full. Override with
--reporter=dot for long suites (test:randomize,
test:fuzz-maintenance) when progress signal matters more than
compactness, or --reporter=default to force the full reporter.
pnpm verify / pnpm test is what humans run before pushing. pnpm verify is split into verify:code (the whole chain minus markdown) and
verify:docs (markdown/mermaid validation); verify runs both. The
lefthook pre-commit hook runs them by glob — verify:code when a
.ts/.tsx file is staged, verify:docs when a .md file is staged
(so a docs-only commit is now validated locally too, and a code-only
commit skips the markdown checks it can't affect) — plus a scoped
pnpm bundle-sizes (see below), but NOT the full pnpm test suite.
pnpm verify:agent / pnpm test:agent are explicit compact-output
variants for environments where the env var isn't propagated.
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 Changed · -2 tokens per session b5dc750fadd2
- 2mo ago First seen · 382 lines · 6,924 tokens per session scan A 07421d5d2020
baerly-storage CLAUDE.md is an instructions file published in the GitHub repository Gusto/baerly-storage (25 stars, last pushed today), licensed Apache-2.0. It adds 6,922 tokens to every session, about $0.0277 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 2026-08-30.
baerly-storage CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| baerly-storage CLAUDE.mdGusto/baerly-storage | Instructions file | 25 | today | Apache-2.0 | A | 6,922 | 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 |