cua AGENTS.md

A set of repository instructions for contributors and coding agents working on the Cua project, including how to preserve authorship and handle GitHub work.

In plain words
What is it for?
Guiding issue and pull-request work, contributor attribution, polling for maintainer tasks, and cross-platform Cua development.
Why use it?
It clarifies the project's contribution and review expectations so changes do not lose credit or bypass the intended workflow.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/trycua/cua/agents-md
Clone the repo
git clone --depth 1 https://github.com/trycua/cua

Made for: Codex, OpenCode.

Per session 2,166 This file is loaded in full into every session.
When invoked 2,166 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02166 $0.02166
Opus 5 $0.01083 $0.01083
Sonnet 5 $0.00433 $0.00433
Haiku 4.5 $0.00217 $0.00217

Measured 2d ago against content hash f50fa0df9229, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cua 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.

AGENTS.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository agent guidance

Contributor authorship

Preserve contributor credit when external code or design ships in Cua.

  • Merge the contributor's pull request when it can land directly.
  • When moving a commit, use git cherry-pick -x <sha> so its author and source commit remain in history.
  • When adapting material parts of a contribution in a new commit, add the contributor with a Co-authored-by trailer and write Salvaged from #<pr> in the commit or landing pull request body. The source pull request must be different from the landing pull request.
  • When adapting a contribution directly in its existing pull request, keep the contributor as the commit author and credit adapting authors with Co-authored-by trailers instead of citing the pull request as its own source.
  • Use GitHub-linked or GitHub noreply email addresses for commit authors and coauthors so the contributor-attribution check can resolve each identity.
  • Preserve known human coauthor trailers during rebases and squash merges.
  • Link the source pull request and tell its author where the work shipped.
  • Honor public credit opt-out requests. Keep security attribution private until disclosure is permitted.

Do not reimplement submitted work solely to remove its authorship history.

Issue and pull request workflow

The human-facing contribution and selection contract lives in CONTRIBUTING.md, MAINTAINERS.md, the GitHub issue forms, rfcs/README.md, and SECURITY.md. Keep those files canonical instead of duplicating their field lists, polling ladder, or RFC lifecycle here.

Coding agents act as workers within that contract, not as a planning authority. GitHub holds the durable record: the issue or RFC carries the problem and the decision, and the pull request carries the execution. Local schedulers, queues, and worktree tooling are private conveniences; a reviewer must not need them to understand, reproduce, or continue the work.

Read the full file on GitHub · 191 lines

Changes

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.

  1. 2d ago First seen · 191 lines · 2,166 tokens per session scan A f50fa0df9229

Subscribe to this mod's changes

cua AGENTS.md is an instructions file published in the GitHub repository trycua/cua (22,024 stars, last pushed 3d ago), licensed MIT. It adds 2,166 tokens to every session, about $0.0108 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.

Related

Other instructions, from other repositories

microsandbox AGENTS.md

AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.

superradcompany/microsandbox · 3,652 tokens

apple-mail-mcp CLAUDE.md

Instructions for sweetrb/apple-mail-mcp, covering claude.md - apple mail mcp server, configuring imap / smtp (when a user asks to set it up), critical: backslash escaping, why this matters and examples.

sweetrb/apple-mail-mcp · 5,071 tokens

the-unofficial-swift-programming-language-skill CLAUDE.md

Instructions for kylehughes/the-unofficial-swift-programming-language-skill, covering claude.md, repository purpose, build commands, generate the skill package and build options.

kylehughes/the-unofficial-swift-programming-language-skill · 1,017 tokens

apple-photos-mcp CLAUDE.md

Instructions for sweetrb/apple-photos-mcp, covering claude.md - apple photos mcp server, related documentation, first-run requirements, performance model: cold vs warm calls and the core workflow: query, then act.

sweetrb/apple-photos-mcp · 5,917 tokens

pyapple-mcp CLAUDE.md

Instructions for 54yyyu/pyapple-mcp, covering claude.md, development commands, installation and development setup, install in development mode with dev dependencies and run the mcp server directly.

54yyyu/pyapple-mcp · 2,956 tokens

orchard-mcp AGENTS.md

Instructions for l22-io/orchard-mcp, covering agents.md, project overview, commands, architecture and key patterns.

l22-io/orchard-mcp · 1,000 tokens