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/apache/pulsar/agents-mdgit clone --depth 1 https://github.com/apache/pulsarWhat 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 | $0.01459 | $0.01459 |
| Opus 5 | $0.00730 | $0.00730 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
pulsar 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide for Apache Pulsar
Supplemental guidance for AI coding assistants (Claude Code, Copilot, Cursor, Gemini, Codex, Aider, and similar tools) working in this repository. Keep this file short — it is a router. The detail lives in the human-facing docs linked below; read the one that fits your task rather than pulling everything into context up front.
Apache Pulsar is a distributed pub-sub messaging and streaming platform. The codebase is performance-critical, heavily asynchronous, and concurrency-sensitive. Prioritize correctness, thread safety, performance, maintainability, and backward compatibility.
Licensing and provenance (read first)
Apache Pulsar is licensed under the Apache License 2.0, and all contributions must meet the ASF's Generative Tooling guidance:
- A human is in the loop and is accountable. Every pull request and every security report must be submitted by a human contributor who has reviewed and verified the change and takes responsibility for it. Fully autonomous agents (e.g. OpenClaw-style bots) opening PRs or filing reports on their own are not acceptable — the AI assists, the human is accountable.
- Don't introduce code of incompatible or unknown provenance. Never copy verbatim from GPL/AGPL/LGPL, proprietary, or unlicensed sources (including Stack Overflow / blog / forum snippets of unclear licensing), and don't use a tool whose terms restrict the output inconsistently with open source. Reimplement from specifications or Apache-compatible sources, and follow the ASF 3rd Party Licensing Policy.
- Every new source file needs the ASF license header (Spotless enforces this — copy the form from
an existing
.javafile). - Consider attributing AI assistance. When AI tooling assisted on a change, consider adding an
Assisted-by: <tool/version>commit trailer (the default, since a human still does the final review);Generated-by: <tool/version>is for minimally-modified generated output.
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 · 88 lines · 1,459 tokens per session scan A 1883b22f54c5
pulsar AGENTS.md is an instructions file published in the GitHub repository apache/pulsar (15,319 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,459 tokens to every session, about $0.0073 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
rocketmq-rust AGENTS.md
Instructions for mxsm/rocketmq-rust, covering agents.md, scope and precedence, repository boundaries, working agreement and rust engineering guardrails.
baguette CLAUDE.md
Instructions for tddworks/baguette, covering claude.md, tdd is non-negotiable (read this first), naming the abstractions, splitting an adapter that wraps 3rd-party i/o and coverage target.
baguette AGENTS.md
Instructions for tddworks/baguette, covering agents.md, tdd is non-negotiable (read this first), naming the abstractions, splitting an adapter that wraps 3rd-party i/o and coverage target.
nuclear AGENTS.md
AGENTS.md instructions for nukeop/nuclear, covering agents.md, project overview, packages, commands and development.
nuclear copilot-instructions.md
Copilot instructions for nukeop/nuclear, covering nuclear music player - copilot instructions, project overview, key features, tech stack and packages.
rabbitmq-server AGENTS.md
AGENTS.md instructions for rabbitmq/rabbitmq-server, covering instructions for ai agents, website and github repositories, building and testing, dialyzer and xref and repository structure.