What is agent-fs CLAUDE.md?

Repository instructions for agent-fs, a Bun monorepo for file-related packages, including a core library, command-line tool, MCP server, and web server. A monorepo stores several related packages in one repository.

Use them when developing, testing, building, releasing, or deploying agent-fs and its packages.

They provide the correct commands and point to the authoritative release and deployment documents, including an important package-manager distinction.

How desplega-ai/agent-fs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to desplega-ai/agent-fs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/desplega-ai/agent-fs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/desplega-ai/agent-fs

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/desplega-ai/agent-fs/claude-md/github.svg)](https://agentmods.dev/instructions/desplega-ai/agent-fs/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/desplega-ai/agent-fs/claude-md"><img src="https://agentmods.dev/badge/instructions/desplega-ai/agent-fs/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/desplega-ai/agent-fs/claude-md"><img src="https://agentmods.dev/badge/instructions/desplega-ai/agent-fs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,522 This file is loaded in full into every session.

When invoked 2,522 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02522	$0.02522
Opus 5.5	$0.01009	$0.01009
Sonnet 5.5	$0.00504	$0.00504
Haiku 4.5	$0.00252	$0.00252

Measured 18d ago against content hash c1fa280774f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-fs 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 18d 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.

CLAUDE.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-fs

See PRODUCT.md for product vision and positioning (agent-fs is to files what agentmail is to email).

Bun monorepo: packages/{core, cli, mcp, server}

Commands

bun install — install dependencies
bun run typecheck — TypeScript type checking (tsc --build)
bun run build — bundle CLI for npm to packages/cli/dist/cli.js
bun run test — run tests (manual/integration tests auto-skip without env)
bun run scripts/e2e.ts "bun run packages/cli/src/index.ts --" — CLI E2E tests (requires Docker for MinIO)
bun run scripts/e2e.ts "bun run packages/cli/src/index.ts --" --local-only — credential-free local-filesystem E2E mode used in CI

Releasing & Deployment

RELEASING.md is the source of truth for the release process — read it before touching versions, release scripts, or the publish workflows. Do not restate its mechanics elsewhere; link to it.

See DEPLOYMENT.md for deployment targets (npm package contents, Docker/GHCR, Fly.io, env vars).

Short version: releases are automatic. A version change landing on main triggers tag + publish.

./scripts/release.sh 0.13.0   # sync every version target, commit, push

Never bump a version by hand-editing package.json — scripts/sync-versions.ts owns every place the version appears, and CI fails a partial bump.

Two more invariants that sync-versions.ts --check enforces on every PR and before every tag (details in RELEASING.md § Version targets): bun.lock workspace versions move with the release version, and the bun version is pinned to the same exact number in package.json packageManager, both Dockerfile FROM oven/bun: tags, and every workflow bun-version:. Never use a floating oven/bun:1.4 tag. Bump the three places together, and run bun install --frozen-lockfile after any dependency or version change so the lockfile is committed with it.

Release Checklist (applies to plans, research, and Plan mode)

Read the full file on GitHub · 106 lines

Changes

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.

18d ago Changed · +4 lines · +176 tokens per session c1fa280774f4
2mo ago Changed · +2 lines · +147 tokens per session 23ee83160027
2mo ago First seen · 100 lines · 2,199 tokens per session scan A b5064a0592b8

Subscribe to this mod's changes

agent-fs CLAUDE.md is an instructions file published in the GitHub repository desplega-ai/agent-fs (24 stars, last pushed yesterday), licensed MIT. It adds 2,522 tokens to every session, about $0.0101 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.

agentic agents filesystem human-in-the-loop llms s3

agent-fs CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-fs CLAUDE.mddesplega-ai/agent-fs	Instructions file	24	yesterday	MIT	A	2,522	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

agent-fs: Instructions file for Claude Code