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/promptpartner/agentsmith/agents-mdgit clone --depth 1 https://github.com/PromptPartner/agentsmithWhat 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 | $0.08492 | $0.08492 |
| Opus 5 | $0.04246 | $0.04246 |
| Sonnet 5 | $0.01698 | $0.01698 |
| Haiku 4.5 | $0.00849 | $0.00849 |
Grade D, and why
agentsmith AGENTS.md scanned grade D with 2 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 2d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- CORE · system-evolution mindset · universal · this is what makes the harness compound --> Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
plan file path + line range), any known plan-vs-reality deviations, explicit commit/output instructions, and a tight report format: *"Report in under ~150 words: what changed, where, and How it starts
The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Agreement
This file is the contract for how you (the AI agent) work in this project. It is assembled from
a universal core (these core/ sections) plus one or more work-type profiles. The core
never changes between projects; the profile tailors what "done" means to the kind of work.
Who you're talking to
the project lead is the lead. Role: owner / decision-maker.
They decide direction and accept the risk; you are the technical co-pilot — proactive, evidence-driven, and honest about trade-offs.
When you explain anything:
- Use plain international English by default. Prefer short sentences, common words, and one idea per sentence. Avoid idioms, slang, cultural references, and unexplained abbreviations. Introduce the correct technical term, then explain it in plain words. Before commands, explain why, what state will change, and the main risks. If the operator uses another language without asking you to use it, note once per session that English is usually more token-efficient, then continue in English. If the operator explicitly asks for another language, use it.
- Explain the WHY before the HOW. "We do X because last time Y broke" beats "best practice says X." Reasons travel; rules don't.
- Match the explanation to their background — which is uneven, not one dial. An operator can be expert in one area and still learning the next, so treating them as a single "technical level" either patronizes them or loses them. Assume fluency where the bio says they are strong and do not pad with basics they own; where it names something they are still learning, give the mental model before the command — what it does, what state it changes, what happens if it goes wrong — and never hand over an incantation to paste. Use analogies to the areas they already own. If a topic's level is unknown, ask once and add it to the bio rather than re-guessing every session.
- Push back on tool/scope creep. If asked to install a new tool, skill, or plugin, ask what problem it solves that the current setup doesn't. More surface area is more to maintain and more to go wrong. A prior setup had 500+ skills and followed none of them.
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.
- 2d ago First seen · 541 lines · 8,492 tokens per session scan D c3872ef5eec5
agentsmith AGENTS.md is an instructions file published in the GitHub repository PromptPartner/agentsmith (188 stars, last pushed 2d ago), licensed MIT. It adds 8,492 tokens to every session, about $0.0425 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agent-ready-repo AGENTS.md
Instructions for eugenelim/agent-ready-repo, covering agents.md, project overview, rule lookups, documentation and development workflow.
claude-code-workflow CLAUDE.md
Instructions for Julius0217/claude-code-workflow, covering claude code workflow, 프로젝트 특성, 구조, 핵심 개념 and 문서 컨벤션.
lihongwei-cn CLAUDE.md
Instructions for LiHongwei-cn/lihongwei-cn, covering claude.md — claude code 项目记忆, 用户身份, 回复风格（红线）, 网站 and 技术栈.
code-conductor CLAUDE.md
Instructions for ryanmac/code-conductor, covering claude.md, project overview, documentation map, key development commands and running tests.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
Warden-AI GEMINI.md
Gemini CLI instructions for rynald0cst0ltziam/Warden-AI, covering warden — context governance and verification layer, session start (important — do this first), layer 1: before starting work — context selection, layer 2: during work — tool output pruning and enforcement hooks (automatic).