agentmods.dev

burrow CLAUDE.md

burrow CLAUDE.md is an instructions file for coding agents from jayminwest/burrow. It costs 1,605 tokens per session, scanned A, original, MIT.

Project instructions for Burrow, a runtime that gives coding agents operating-system-level isolation. They describe its TypeScript and Bun setup, build commands, tests, linting, type checking, and code conventions.

In plain words
What is it for?
Working on Burrow, running its tests, formatter and linter, and TypeScript checks, and following its strict TypeScript conventions and sandbox choices.
Why use it?
They give an agent the project rules and verification commands it needs to make compatible changes. They also explain the checks required before committing so common quality problems are caught early.

Instructions file

not rated 12 1mo ago A scan 1,605 tokens original MIT
View the source file jayminwest/burrow
Install

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.

agentmods
npx agentmods add instructions/jayminwest/burrow/claude-md
Clone the repo
git clone --depth 1 https://github.com/jayminwest/burrow

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.

agentmods badge for burrow CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jayminwest/burrow/claude-md.svg)](https://agentmods.dev/instructions/jayminwest/burrow/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jayminwest/burrow/claude-md"><img src="https://agentmods.dev/badge/instructions/jayminwest/burrow/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,605 This file is loaded in full into every session.
When invoked 1,605 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01605 $0.01605
Opus 5 $0.00803 $0.00803
Sonnet 5 $0.00321 $0.00321
Haiku 4.5 $0.00161 $0.00161

Measured 4d ago against content hash b5e6410505b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

burrow 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.

CLAUDE.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Burrow

OS-isolated sandbox runtime for coding agents. SPEC.md is the frozen V1 design record; ROADMAP.md is the punch list of forward-looking items. New deferred decisions out of design discussions land in ROADMAP.md as R-NN items rather than as standalone informational seeds.

Tech Stack

  • Runtime: Bun (runs TypeScript directly, no build step)
  • Language: TypeScript with strict mode (noUncheckedIndexedAccess, no any)
  • Linting: Biome (formatter + linter; lint script runs --error-on-warnings, so warnings fail CI)
  • Storage: SQLite via bun:sqlite for session/event persistence
  • Sandbox primitives: bwrap (Linux), sandbox-exec (macOS) — no Docker, no daemon

Build & Test Commands

bun test                      # Run all tests
bun test src/foo.test.ts      # Run a single test file
bun run lint                  # biome check --error-on-warnings .
bun run typecheck             # tsc --noEmit

Quality Gates

Run all three before committing — warnings count as failures:

bun test && bun run lint && bun run typecheck

CI runs the same trinity. Don't merge with lint warnings; promote to error in biome.json or fix at write time.

TypeScript Conventions

  • Strict mode with noUncheckedIndexedAccess — always handle possible undefined from indexing
  • No any — use unknown and narrow, or define proper types
  • All shared types in src/types.ts
  • Import with .ts extensions
  • Tab indentation, 100-char line width (enforced by Biome)

Version Management

Version lives in two places (kept in sync by scripts/version-bump.ts and verified by the publish workflow):

  • package.json — "version" field
  • src/index.ts — const VERSION = "X.Y.Z"

Bump via: bun run version:bump <major|minor|patch>

Session Completion Protocol

When ending a work session, complete ALL steps:

  1. File issues for remaining work: sd create --title "..."
  2. Run quality gates (if code changed): bun test && bun run lint && bun run typecheck
  3. Close finished issues: sd close <id>
  4. Push: sd sync && git push
  5. Verify: git status shows "up to date with origin"

Read the full file on GitHub · 151 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.

  1. 4d ago First seen · 151 lines · 1,605 tokens per session scan A b5e6410505b5

Subscribe to this mod's changes

burrow CLAUDE.md is an instructions file published in the GitHub repository jayminwest/burrow (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,605 tokens to every session, about $0.0080 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 2026-08-30.

ai-agentsdeveloper-toolssandbox
Related

Other instructions, from other repositories

OpenSandbox AGENTS.md

AGENTS.md instructions for opensandbox-group/OpenSandbox, covering opensandbox agents, repository map, routing, working principles and guardrails.

opensandbox-group/OpenSandbox · 1,693 tokens

microsandbox AGENTS.md

AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.

superradcompany/microsandbox · 3,652 tokens

agentos CLAUDE.md

Claude Code instructions for rivet-dev/agentos, covering agentos, boundaries, security model, sqlite schema ownership and runtime and registry.

rivet-dev/agentos · 4,057 tokens

OpenSandbox CLAUDE.md

Claude Code instructions for opensandbox-group/OpenSandbox: See AGENTS.md for all rules, routing, and conventions.

opensandbox-group/OpenSandbox · 21 tokens

agent-safehouse AGENTS.md

AGENTS.md instructions for eugene1g/agent-safehouse, covering agent safehouse: llm quick reference, what this project is, fast working rules, core commands and generate policy only (prints temp policy path).

eugene1g/agent-safehouse · 1,350 tokens

agent-sandbox AGENTS.md

AGENTS.md instructions for kubernetes-sigs/agent-sandbox, covering agents.md, project summary, repository layout, agent skills and build, test, lint.

kubernetes-sigs/agent-sandbox · 4,327 tokens