agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Worked for most · soon
autonomous-aiAGENTS.md

autonomous-harness

autonomous-ai/autonomous-harness/AGENTS.md

Follow CONTRIBUTING.md and the component's instructions. For validation and shipping, use docs/validation-and-release.md. For product names, terminology, and visible copy, follow the Naming System. - Measure the user's request through completion. Record implementation, validation, merge, publication, and waiting separately; an Actions duration is not the total. - Choose the necessary checks before starting them. Run affected tests and relevant integration checks; use full suites for broad changes. Start independent checks together within the machine's capacity. Do not add a second full…

1.4k17d agoReviewMountCreate a free account to mount
autonomous-aiAGENTS.md

autonomous-harness / cli

autonomous-ai/autonomous-harness/cli/AGENTS.md

Read this before changing anything under cli/. The repository-wide process rules (validation, merging, releases) are in ../AGENTS.md. The design, and why, is in ../docs/design/2026-10-03-harnessd.md. The one-page picture for new contributors is ../docs/design/2026-10-04-harnessd-before-after.md. The master runs the core and every service process (SERVICE_HOSTS in src/harnessd/services.ts). Each service process runs one or more services, each on its own link to the core. In Activity Monitor and ps they show as harnessd, harnessd-core and harnessd-<process> (src/harnessd/processName.ts). HARNESSDSERVICES names a subset to run in…

Steady38 mentions in 2 weeks

No other project uses it yet

1.4k17d agoReviewMountCreate a free account to mount
autonomous-aiAGENTS.md

autonomous-harness / desktop

autonomous-ai/autonomous-harness/desktop/AGENTS.md

Use CLAUDE.md for architecture, build commands, and testing. For DSH dashboards, follow the DSH workspace contract: 70% viewer on the left, 30% real agent chat on the right, including loading, missing dependencies, failures, retries, and restoration. Reserve the chat slot before startup; never let an unavailable conversation become a full-width viewer. The Swarm's Your devices is a dashboard-only exception: fill its center pane, keep the sidebars visible, and do not start or reserve a Devices conversation. Standalone Devices retains its…

Steady38 mentions in 2 weeks

No other project uses it yet

1.4k17d agoReviewMountCreate a free account to mount
autonomous-aiAGENTS.md

autonomous-harness / store

autonomous-ai/autonomous-harness/store/AGENTS.md

Before creating or changing a DSH, read the authoring guide and the DSH workspace contract. A DSH dashboard always has the real agent chat to its right, initially 70% viewer and 30% chat. Loading or failed setup must keep that chat slot and show recovery there. Verify the whole workspace, including failures, rather than only the viewer. Package AGENTS.md files describe the materialized agent's job; they do not replace this desktop integration contract.

Steady38 mentions in 2 weeks

1 project uses a version of this

1.4k17d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.