Agently-Skills
AgentEra/Agently-Skills/AGENTS.md
Central catalog and documentation for Agently Skills V3. Use when working with Agently skill installation, routing, and installed-skill usage guidance.
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
AgentEra/Agently-Skills/AGENTS.md
Central catalog and documentation for Agently Skills V3. Use when working with Agently skill installation, routing, and installed-skill usage guidance.
johnfkoo951/cmds-llm-wiki/AGENTS.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.
jrodrigopuca/local-agents/visionary/AGENTS.md
Use this agent for product vision, brutally honest product critique, ruthless focus and prioritization, and inspiration. Modeled on Steve Jobs's documented thinking — hard on the work, never on the person. Speaks product, not implementation.
gtapps/skills/skills/wrap/references/agents.md
Close an operator session on disk. Classify learnings verified vs idea and route them (personal memory, or the destination the project's instructions name), run the project's mandated close (proposal-act, GUEST_REPORT) and show its output, refresh the final-plan-check gauntlet with any question that bounced a plan this session, write the loose-ends line, give the plan file its issue name, print a five-line close. Trigger on "/wrap", "save learnings", "save this as a learning", "wrap this up", "wrap up", "close the session", and proactively before ending any session that produced a verdict, a plan, or a measurement. Do NOT use to commit or push (commit, commit-push), to open a PR (open-pr), or to write a handoff document for another agent (handoff).
steipete/clawdis/AGENTS.md
only at egress (logs.tail, diagnostics/support bundles, remote/OTel export); never log message/tool content. - Plugins use documented `openclaw/plugin-sdk/*` contracts, manifest metadata, public/local barrels; never core internals or another plugin's private files
steipete/clawdis/ui/AGENTS.md
pointer cursors; state-changing controls: default arrow. - Colors: use `src/styles/base.css` tokens. - `main.runtime.ts` injects `components/kbd.css` document-wide; renderers never import it. Never JS-import a sheet `styles.css` already ships from
moltbot/moltbot/AGENTS.md
only at egress (logs.tail, diagnostics/support bundles, remote/OTel export); never log message/tool content. - Plugins use documented `openclaw/plugin-sdk/*` contracts, manifest metadata, public/local barrels; never core internals or another plugin's private files
1 project uses a version of this
steipete/warelay/AGENTS.md
only at egress (logs.tail, diagnostics/support bundles, remote/OTel export); never log message/tool content. - Plugins use documented `openclaw/plugin-sdk/*` contracts, manifest metadata, public/local barrels; never core internals or another plugin's private files
3 projects use a version of this
molt-bot/clawdbot/AGENTS.md
beta, and nightly code are not shipped contracts. ## Runtime and code safeguards - Plugins use documented `openclaw/plugin-sdk/*` contracts, manifest metadata, and public/local barrels, never core internals or another plugin's private
1 project uses a version of this
molt-bot/clawdbot/docs/AGENTS.md
root `AGENTS.md`. - CI verifies JSON5 and JSON config fences that look like whole `openclaw.json` documents against the schema. `pnpm docs:check-config-examples` runs that verification. Deliberately partial or legacy
3 projects use a version of this
morluto/rea/AGENTS.md
fast`: cached typecheck/lint and the pre-push check. - `npm run docs:check`: validate generated documentation. Use relevant checks for the change. The complete local gate, `npm run check
Steady36 mentions in 2 weeks
No other project uses it yet
obra/superpowers/AGENTS.md
what produced a change in order to weigh it: agent-generated content reasoned from documentation is held to a different bar than work grounded in a real session. Contributions that
Steady3 mentions in 2 weeks
No other project uses it yet
deepseek-ai/deepseek-harness/AGENTS.md
plugin Cordis agent harness. Read [docs/architecture.md](docs/architecture.md) before changing `packages/`; follow [docs/AGENTS.md](docs/AGENTS.md) for documentation. ## Pre-stable APIs and released Session data Public APIs are pre-stable; update every consumer
deepseek-ai/deepseek-harness/.agents/notes/AGENTS.md
proposals and decision records that preserve rationale, alternatives, consequences, and required verification. Follow the [documentation standard](../../docs/AGENTS.md) and the [Agent Note rules](README.md). **Every new Agent Note triggers a supersession
Steady8 mentions in 2 weeks
8 projects use a version of this
deepseek-ai/deepseek-harness/.agents/notes/archived/AGENTS.md
repair, delete, or move a sealed artifact; use an active Agent Note or current documentation for new decisions and facts. The archival change may only relocate a complete English/Chinese/sidecar triplet
Steady8 mentions in 2 weeks
1 project uses a version of this
deepseek-ai/deepseek-harness/.agents/notes/implemented/AGENTS.md
Implemented Agent Notes These Agent Notes describe shipped decisions. Follow the [root instructions](../../../AGENTS.md), [documentation standard](../../../docs/AGENTS.md), and [Agent Note format](../README.md#the-file-format); `verify-agent-note-format` gates
Steady8 mentions in 2 weeks
8 projects use a version of this
deepseek-ai/deepseek-harness/docs/AGENTS.md
AGENTS.md — The documentation standard This file defines document structure, Markdown tiers, writing rules, and `verify-doc-budgets` ceilings. Use [dsh-doc](../.agents/skills/dsh-doc/SKILL.md) for placement and validation, and [dsh-prose-standard
deepseek-ai/deepseek-harness/packages/AGENTS.md
subsystem ownership through a canonical English page link or justified [exemption](../scripts/verify-subsystem-pages.ts). - Package READMEs document model, token, and KV-cache effects using the [canonical Model Experience format](../docs/cookbook/adding-a-package.md#4-write
Steady8 mentions in 2 weeks
1 project uses a version of this
deepseek-ai/deepseek-harness/packages/client/AGENTS.md
Definition republishes the block when an observed answer changes. Transient file-read and document-preview content may also carry `Uint8Array`: published buffers are borrowed read-only, copied before Worker transfer
deepseek-ai/deepseek-harness/packages/experimental/AGENTS.md
through `devDependencies`; examples may load them explicitly. - Experimental status does not relax engineering, security, documentation, lifecycle, testing, or snapshot requirements. - Publishing an experimental package does not promote
Steady8 mentions in 2 weeks
No other project uses it yet
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.