Borrowing it
Nothing to install: this file belongs to a2uicatalog/a2ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/a2uicatalog/a2ui/main/AGENTS.mdgit clone --depth 1 https://github.com/a2uicatalog/a2uiWrote 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/a2uicatalog/a2ui/agents-md)<a href="https://agentmods.dev/instructions/a2uicatalog/a2ui/agents-md"><img src="https://agentmods.dev/badge/instructions/a2uicatalog/a2ui/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/a2uicatalog/a2ui/agents-md"><img src="https://agentmods.dev/badge/instructions/a2uicatalog/a2ui/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00797 | $0.00797 |
| Opus 5.5 | $0.00319 | $0.00319 |
| Sonnet 5.5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
a2ui 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 2mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a2ui-catalogue — Agent Entry Point
This file exists so that ANY coding agent (Gemini, Antigravity, Codex, Claude, …)
finds the working rules. The canonical rules live in CLAUDE.md — read it in full
before doing anything. project.yaml is the inventory (deployments, script IDs,
policy, declared processes); never carry identifiers from conversation memory when
the manifest declares them.
Non-negotiables (summary — CLAUDE.md is authoritative)
-
Every operation goes through a declared process.
python3 ops/ops.py list→python3 ops/ops.py run <process>. If the operation you need is not declared, declare it inproject.yamlprocesses:first, then run it. Rawclasp push/clasp deployor ad-hoc command chains are forbidden — improvisation is the failure mode this system exists to prevent. "ops.py run X or standard clasp push" is not a plan; it is the bug. -
Nothing new is published to a2uicatalog.ai or any public surface without explicit per-artifact opt-in from Curtis (
policy.publishedinproject.yaml, enforced by tests). Nevergit add -A. Commits go throughpython3 ops/ops.py commit "<msg>"; push throughops.py run repo-publish. -
Renderer source is ground truth. When
atoms/schema.yamlprose and a renderer.gsfile disagree about a field shape, the renderer wins (known case:spring_nodesedges are{from, to}node IDs, not the documented{a, b}index pairs). -
Verify before shipping:
python3 -m pytest tests/ -q. Checkops/log.jsonlbefore re-diagnosing anything — a previous run may have already recorded it. -
Encoded
?p=URLs are emitted byscripts/make_url.pyonly — never hand-typed or copied between surfaces. -
Mutating git commands must name the repo explicitly:
git -C <path> add|commit|push. Ambient cwd and a leadingcddo not count — the shell cwd resets between calls. Commits and pushes go through the declared processes in rule 2, never raw git.
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.
- 2mo ago First seen · 57 lines · 797 tokens per session scan A 12ef3a390f06
a2ui AGENTS.md is an instructions file published in the GitHub repository a2uicatalog/a2ui (6 stars, last pushed 5d ago), licensed MIT. It adds 797 tokens to every session, about $0.0032 per session on Opus 5.5. 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.
a2ui AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| a2ui AGENTS.mda2uicatalog/a2ui | Instructions file | 6 | 5d ago | MIT | A | 797 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |