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/e0ipso/strikethroo/agents-mdgit clone --depth 1 https://github.com/e0ipso/strikethrooWrote 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/e0ipso/strikethroo/agents-md)<a href="https://agentmods.dev/instructions/e0ipso/strikethroo/agents-md"><img src="https://agentmods.dev/badge/instructions/e0ipso/strikethroo/agents-md.svg" alt="Measured on agentmods" 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 | $0.13723 | $0.13723 |
| Opus 5 | $0.06862 | $0.06862 |
| Sonnet 5 | $0.02745 | $0.02745 |
| Haiku 4.5 | $0.01372 | $0.01372 |
Grade A, and why
strikethroo AGENTS.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 today.
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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Primary context source for AI-assisted work in this repository.
Quick Start
# Build, then run any of the four commands
npm run build
npm start init --harnesses claude --destination-directory /path/to/project # --force to overwrite all
node dist/cli.js export profile --destination-directory /path/to/package
node dist/cli.js serve # or: npx strikethroo serve
node dist/cli.js validate # --workspace <path>, --json
# Development
npm run dev # Watch mode compilation
npm test # Full gate: unit (Vitest) then e2e (@playwright/test)
npm run lint:fix # Auto-fix style
init bootstraps the .ai/strikethroo/ workspace (and copies Claude agents); it does not install skills. It uses SHA-256 hash tracking in .ai/strikethroo/.init-metadata.json to detect and protect user-modified files; --force bypasses the prompts for automation.
The CLI registers four commands (src/cli.ts): init, the nested export profile, serve, and validate. Every action stays thin — it parses flags, delegates to a module, and owns only the reporting and the exit code.
The workflow ships as harness-agnostic Agent Skills, installed with npx skills add e0ipso/strikethroo — see Distribution for how the Git tree serves this. Append #<git-ref> to install from a specific branch or tag (e.g. #v3.19.1) using the installer's own Git-ref syntax; @<name> filters by skill name.
Glossary
- Work order — The user's request describing what they want accomplished.
- Plan — Comprehensive document covering requirements, architecture, risks, and success criteria.
- Execution blueprint — All tasks organized into dependency-mapped phases. Output of task generation.
- Phase — A group of tasks that execute in parallel. Phases run in sequence.
- Task — An atomic unit of work with 1-2 skills and clear acceptance criteria. Executed by a sub-agent.
- Sub-agent — A specialized AI agent executing a single task with focused, clean context.
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.
- today Changed · +4 lines · +198 tokens per session 74b3b5a0ea8c
- 4d ago First seen · 383 lines · 13,525 tokens per session scan A 1f5549b94dfe
strikethroo AGENTS.md is an instructions file published in the GitHub repository e0ipso/strikethroo (48 stars, last pushed yesterday), licensed MIT. It adds 13,723 tokens to every session, about $0.0686 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
Perigon.CLI copilot-instructions.md
Copilot instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.
gemini-kit GEMINI.md
Instructions for nth5693/gemini-kit, covering gemini-kit: super engineer team, role & responsibilities, workflows, team members and workflow.
harmont-cli CLAUDE.md
Instructions for harmont-dev/harmont-cli, covering testing, documentation, dsl and keep the sdk, hm init templates, and docs in sync.
HarnessSmith CLAUDE.md
Instructions for EpisodeYu/HarnessSmith, covering claude.md — harnesssmith 项目守则, 0. 协作模式与角色边界, 0.1 只能由人配置的环境(agent 不代劳), 1. think before coding and 2. thin first(薄优先 —— 本项目核心卖点,硬约束).
hermes-model-auto-switch AGENTS.md
Instructions for rhishi99/hermes-model-auto-switch, covering install, verify, uninstall, guardrails and conventions.