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/the-open-engine/zeroshot/claude-mdgit clone --depth 1 https://github.com/the-open-engine/zeroshotWhat 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 | $0.06104 | $0.06104 |
| Opus 5 | $0.03052 | $0.03052 |
| Sonnet 5 | $0.01221 | $0.01221 |
| Haiku 4.5 | $0.00610 | $0.00610 |
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 yesterday.
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 — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UPDATE THIS FILE when making architectural changes, adding patterns, or changing conventions.
Zeroshot: Multi-Agent Coordination Engine
Message-passing primitives for multi-agent workflows. Install: npm i -g @the-open-engine/zeroshot or npm link (dev).
🔴 CRITICAL RULES
| Rule | Why | Forbidden | Required |
|---|---|---|---|
| GENERAL PURPOSE ONLY | Zeroshot runs on ANY repo | Hardcoded paths, scripts, languages, domains | Discover from target repo's CLAUDE.md/README |
| Never spawn without permission | Consumes API credits | "I'll run zeroshot on 123" | User says "run zeroshot" |
| Never use git in validators | Git state unreliable | git diff, git status in prompts |
Validate files directly |
| Never ask questions | Agents run non-interactively | AskUserQuestion, waiting for confirmation |
Make autonomous decisions |
| Never edit CLAUDE.md | Context file for Claude Code | Editing this file | Read-only unless explicitly asked to update docs |
| Preserve copy containment | Copy paths cross trust boundaries | Independent path joins or one-time checks | Reuse the pinned-root boundary and revalidate immediately before every filesystem effect |
🔴 GENERAL PURPOSE REQUIREMENT (CRITICAL)
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.
- yesterday First seen · 679 lines · 6,104 tokens per session scan A 980f2d654a6d
zeroshot CLAUDE.md is an instructions file published in the GitHub repository the-open-engine/zeroshot (1,811 stars, last pushed yesterday), licensed MIT. It adds 6,104 tokens to every session, about $0.0305 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.
Other instructions, from other repositories
babysitter AGENTS.md
Instructions for a5c-ai/babysitter, covering agents.md, repo-specific overrides, reference map and quick commands.
warren AGENTS.md
Instructions for jayminwest/warren, covering agents.md, what this project is, runtime topology, the burrow absorption (plan pl-3007) and per-project config (.warren/config.yaml).
VisionClaw-Agent-Public-Release AGENTS.md
Instructions for Huskyauto/VisionClaw-Agent-Public-Release, covering agents.md — working in the visionclaw codebase, identity, the cardinal discipline: search before reading, hard rules (non-negotiable) and architecture map (entrypoints).
factory CLAUDE.md
Instructions for watt-mind/factory: Claude, please refer to AGENTS.md and docs/protocol.md for the primary repository context, architecture, commands, operational rules, and tracker issue management standards.
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.
babysitter CLAUDE.md
Instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.