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/initxy/noeta/agents-mdgit clone --depth 1 https://github.com/initxy/noetaWhat 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 | $0.00928 | $0.00928 |
| Opus 5 | $0.00464 | $0.00464 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
noeta 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 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.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication
- Keep answers concise and direct; lead with the conclusion and the next step.
- Don't add unrelated explanation; when unsure, state your assumptions and the risks.
- Conversation may happen in whatever language the other side uses; everything committed to the repo (see Language) is English.
Language
- All repository artifacts are written in English: docs (
CONTEXT.md,docs/adr/,docs/implementation-specs/), handoff notes, code comments, and identifiers. The only exceptions are the Chinese mirrors —README.zh-CN.md,docs/zh/**,docs/releasing.zh.md. - Keep technical terms in their canonical English form and spell them consistently throughout: code identifiers (function / class / file / variable names), API / library / tool / command names, file paths, and fixed architecture terms (module, interface, seam, adapter, deep module, etc.). Don't invent alternate names or switch between synonyms.
- Write clear, idiomatic English prose — not word-for-word translation from another language.
- Pick one spelling per term and use it everywhere; don't mix variants.
- Naming is enforced:
scripts/lint-naming.pyrejectsclass Run/Workflow/Session/Mutator/Pattern, the identifiersWorkflowRunner/WorkflowPolicy/WorkflowSpec/SessionStore/ConversationManager, and — insidepackages/andexamples/— session-compound identifiers outside the allow-list. The canonical names areTaskandroot_task_id; see CONTEXT.md, "Flagged ambiguities".
Workflow
- When the idea isn't clear yet, first converge on a short spec: the goal, scope, key decisions, and acceptance criteria.
- Once the goal is clear, implement against that spec; for large tasks with clean boundaries, split work across subagents while the main agent integrates and verifies.
- When done, review the result against the spec, the actual code changes, and the verification output (
make check; see CONTRIBUTING.md). - For architecture improvements, refactoring direction, and module design, start from the existing decisions (see Context / ADR) and the engineering constraints below; when work must continue in a later session, leave a written handoff of current state, decisions made, and next steps.
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 · 43 lines · 928 tokens per session scan A 6f0825cacb3c
noeta AGENTS.md is an instructions file published in the GitHub repository initxy/noeta (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 928 tokens to every session, about $0.0046 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 2026-08-31.
Other instructions, from other repositories
Jixu AGENTS.md
Instructions for joe960913/Jixu, covering jixu repository instructions, 1. read order, 2. sources of truth, 3. canonical concepts and 4. architecture invariants.
Jixu CLAUDE.md
Instructions for joe960913/Jixu, a project described as: Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.