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/alibaba/nacos/agents-mdgit clone --depth 1 https://github.com/alibaba/nacosWhat 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 | $0.06338 | $0.06338 |
| Opus 5 | $0.03169 | $0.03169 |
| Sonnet 5 | $0.01268 | $0.01268 |
| Haiku 4.5 | $0.00634 | $0.00634 |
Grade A, and why
nacos 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 3d 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 — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, GitHub Copilot, etc.) when working with the Nacos repository. For human contributors, see CONTRIBUTING.md.
AI Contribution Guidelines
- Do NOT post AI-generated comments on issues or PRs. Discussions are for humans only.
- Discuss before implementing: Ensure the implementation direction is agreed upon with maintainers in the issue comments before starting work.
- Spec-first coding is mandatory: Before changing behavior, APIs, SDKs,
plugins, storage, runtime flow, or domain semantics, AI agents MUST read the
relevant specs under
specs/and treat them as the rule source for the implementation. - Discuss spec-impacting changes before coding: If a change touches behavior covered by an existing spec, or exposes a gap between the code and the spec, AI agents MUST discuss the implementation direction and the required spec update with maintainers before starting the code change.
- Update specs with the design: Any design proposal that changes or clarifies spec-covered behavior MUST include the corresponding spec updates in the same change set. When the design is large or controversial, prefer a spec/design-only PR first, then follow with implementation PRs.
- API IT impact comes first: Before adding, changing, deleting, or
deprecating any HTTP API, AI agents MUST analyze the affected
test/openapi-testcoverage and update the API IT scenario matrix, test cases, and coverage registry in the same change set. If the functional path cannot be exercised in standalone IT, cover boundary/error scenarios and document the reason. - Java SDK IT impact comes first: Before adding, changing, deleting, or
deprecating any public Java SDK interface, factory, model, listener behavior,
lifecycle behavior, or exception mapping, AI agents MUST analyze and update
test/java-sdk-testcoverage, including scenario documentation. If the end-to-end success path is impractical, cover SDK parameter validation, boundary behavior, and controlled exceptions. - Disclose AI usage: When a significant part of a commit is AI-generated, add a trailer to your commit message:
Assisted-by: Claude Code - Follow CONTRIBUTING.md for all contribution processes.
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.
- 3d ago First seen · 463 lines · 6,338 tokens per session scan A c2837586006a
nacos AGENTS.md is an instructions file published in the GitHub repository alibaba/nacos (33,337 stars, last pushed yesterday), licensed Apache-2.0. It adds 6,338 tokens to every session, about $0.0317 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
arkade AGENTS.md
Instructions for alexellis/arkade, covering types of arkade commands, 1. how to add a new cli (tool) to arkade, what can be added, prerequisites and step 1: check github releases.
apisix AGENTS.md
Instructions for apache/apisix, covering apache apisix — agent instructions and security model.
qiankun CLAUDE.md
Instructions for umijs/qiankun: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
OpenSandbox CLAUDE.md
Claude Code instructions for opensandbox-group/OpenSandbox: See AGENTS.md for all rules, routing, and conventions.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, mandatory development principles and sow system.
timoni AGENTS.md
AGENTS.md instructions for stefanprodan/timoni, covering agents.md, what timoni is, common commands, architecture and cmd/timoni/ — cli (cobra).