agentmods.dev

zeroshot: Instructions file for Claude Code

CLAUDE.md

zeroshot CLAUDE.md is an instructions file for Claude Code from the-open-engine/zeroshot. It costs 658 tokens per session, scanned A, original, MIT.

A project guide for Zeroshot, a general-purpose engine that coordinates multiple coding agents through message passing. It lists safety and design rules, including permission before spawning agents and protection against unsafe file operations.

In plain words
What is it for?
Use it when coordinating multiple agents, discovering rules from a target repository, validating files, and handling filesystem boundaries or permissions.
Why use it?
It helps agents use the coordination engine safely across different repositories without assuming a particular language, path, or project type.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is the-open-engine/zeroshot's own configuration. It tells Claude Code how to work on zeroshot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zeroshot configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../...

not rated 2.1krepo +37 changed 1mo ago A scan 658 tokens original MIT
View source ↗ the-open-engine/zeroshot zeroshot.sh
About the project

Zeroshot is a software-change orchestration tool that separates implementation from verification: one coding agent makes a change and another independently checks whether it works. Developers use it to run coding tasks in isolated Git worktrees and continue the executor–verifier loop until the result is verified or a concrete failure is reported. The catalogue includes instructions, a hook, a skill, a setting, and a command for Zeroshot.

the-open-engine/zeroshot · 2,114 stars · on GitHub · zeroshot.sh

Reuse

Borrowing it

Nothing to install: this file belongs to the-open-engine/zeroshot. 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/the-open-engine/zeroshot/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/the-open-engine/zeroshot

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.

agentmods badge for zeroshot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/the-open-engine/zeroshot/claude-md/github.svg)](https://agentmods.dev/instructions/the-open-engine/zeroshot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/the-open-engine/zeroshot/claude-md"><img src="https://agentmods.dev/badge/instructions/the-open-engine/zeroshot/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.

agentmods 80×15 button for zeroshot CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/the-open-engine/zeroshot/claude-md"><img src="https://agentmods.dev/badge/instructions/the-open-engine/zeroshot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 658 This file is loaded in full into every session.
When invoked 658 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00658 $0.00658
Opus 5.5 $0.00263 $0.00263
Sonnet 5.5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 1mo ago against content hash 121db12e9613, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zeroshot 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 1mo 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zeroshot v8 — Claude Guidance

AGENTS.md is authoritative. Follow it before this file.

Product

  • Zeroshot v8 is the Rust product in zeroshot/ and owns the zeroshot CLI.
  • Install with npm i -g @the-open-engine-company/zeroshot.
  • Node.js is repository tooling and npm binary delivery only.
  • Python distribution: the-open-engine-zeroshot; import: zeroshot.
  • Target image: ghcr.io/the-open-engine/zeroshot-target.
  • Releases use explicit vX.Y.Z tags with major version 8 or newer.

Do not restore the retired Node product, compatibility aliases, migration, legacy commands, dual release trains, semantic-release, or a dev branch workflow.

Non-Negotiable Rules

  • Never run zeroshot run without explicit user permission.
  • Agents are non-interactive; make scoped autonomous decisions.
  • Normal development and release work targets main.
  • Use git only inside the current isolated worktree. Never use git inside validator prompts.
  • Preserve exact source provenance, bounded values, cancellation safety, and explicit overflow.
  • Treat provider/model identifiers as opaque. Do not maintain model catalogs or infer harnesses.
  • Protocol Rust types are authoritative; regenerate protocol artifacts through the Rust testkit.
  • Regenerate CLI docs with the Rust example; never hand-edit generated CLI Markdown or HTML.
  • Keep release recovery fail-closed: existing immutable outputs must match exact source bytes.

Repository Map

Area Path
Product and CLI zeroshot/
Protocol crates crates/
Protocol fixtures protocol/openengine-cluster/v1/
npm package npm/zeroshot/
Python SDK sdks/python/
Target image docker/zeroshot-target/
Target manifest distribution/zeroshot-targets.json
Distribution tooling scripts/distribution.js
CI .github/workflows/ci.yml
Product release .github/workflows/release.yml
Python release .github/workflows/release-python.yml
Tooling tests tests/tooling/

Read the full file on GitHub · 70 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. 1mo ago Changed · +3 lines · +13 tokens per session 121db12e9613
  2. 1mo ago Changed · -612 lines · -5,459 tokens per session 4c655e0ffcaa
  3. 2mo ago First seen · 679 lines · 6,104 tokens per session scan A 980f2d654a6d

Subscribe to this mod's changes

zeroshot CLAUDE.md is an instructions file published in the GitHub repository the-open-engine/zeroshot (2,114 stars, last pushed yesterday), licensed MIT. It adds 658 tokens to every session, about $0.0026 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.

Building agentsagent-orchestrationagentic-workflowai-agentsclaudecodexdeveloper-tools
Related

zeroshot CLAUDE.md compared with instructions from other repositories

zeroshot CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
zeroshot CLAUDE.mdthe-open-engine/zeroshotInstructions file2.1kyesterdayMITA658Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode