How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
DatabricksAGENTS.mddatabricks/appkit/docs/docs/plugins/agents.md
plus any bundled reference files: ``` server/agents/ skills/ # shared pool — any agent can opt in pdf-forms/ SKILL.md reference.md planner/ agent.md skills/ # private to the `planner` agent house-style/ SKILL.md
GoogleAGENTS.mdgoogle-gemini/gemini-managed-agents-templates/document-processor/AGENTS.md
files** (e.g. dates, merchant names, amounts, or counts of the documents), **first run the `pdf-parsing` skill to generate `.agents/workspace/parsed_invoices.json`** if it does not already exist. Then, write Python code
johnfkoo951AGENTS.mdjohnfkoo951/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.
ThreeMoonsLabAGENTS.mdThreeMoonsLab/agents-shipgate/AGENTS.md
# Agents Shipgate · Agent Instructions Authoritative instructions for AI coding agents (Claude Code, Codex, Cursor
LangChainAGENTS.mdlangchain-ai/paid-media-agent/AGENTS.md
renderer tokens aligned in the same change. Reuse those tokens in HTML, SVG, and PDF; do not introduce a separate palette or font in individual reports. Preserve the accepted appearance
gutomecAGENTS.mdgutomec/nirvana-os-engine/AGENTS.md
invoke the harness skill When the user asks for **any concrete artifact** — book, video, PDF, post, copy, design, illustration, brand, code, page, app, report, analysis, research, dataset, audit, anything — invoke
gutomecAGENTS.mdgutomec/nirvana-os-engine/skills/_shared/templates/AGENTS.md
invoke the harness skill When the user asks for **any concrete artifact** — book, video, PDF, post, copy, design, illustration, brand, code, page, app, report, analysis, research, dataset, audit, anything — invoke
dralkhAGENTS.mddralkh/seerai/AGENTS.md
endpoints, register cloud OAuth callbacks, start background RAG indexer - `onMainWindowLoad()` → context menus (OCR, search PDF, tags, table add/remove, systematic review add/remove), toolbar buttons, theme observer - `onShutdown()` → cleanup (stop background indexer
ankitcharoliaAGENTS.mdankitcharolia/kiro-gateway/AGENTS.md
mimes are decoded and injected; PDFs are extracted via `pypdf` (a standard dependency — `_extract_pdf_text`, lazy import for graceful degradation); a scanned/no-text PDF, other binary formats, and audio
p3botAGENTS.mdp3bot/snag/AGENTS.md
visible browser modes - Handle authenticated sessions gracefully - Multiple output formats: Markdown (default), HTML, Text, PDF, PNG - Multiple URL support: Process multiple URLs in a single command - Tab management: List, select
mgiffordAGENTS.mdmgifford/ACCESSIBILITY.md/AGENTS.md
Pages, editors, and export pipelines as separate surfaces. - Inspect final SVG, raster, print, and PDF output as applicable. ### Generated assets Record source revision, renderer or generator version, configuration, security profile
BENZEMA216AGENTS.mdBENZEMA216/ai-ecommerce-agent-skills/workspace-config/AGENTS.md
WITHIN 产品图：`/root/.openclaw/design-assets/seek-within/photos-inbound/` - SEEK WITHIN 参考图：`/root/.openclaw/design-assets/seek-within/references/` - SEEK WITHIN 原始拍摄：`/root/.openclaw/design-assets/seek-within/photos/` - SEEK WITHIN catalog PDF：`/root/.openclaw/design-assets/seek-within/catalogs/` - 资产索引：`/root/.openclaw/design-assets/seek-within/asset-catalog.json` ## Session 任务交接协议 **触发条件：** 任何时候任务进行到一半但还没完成（比如被打断、切换话题、或感觉 context 快满了） **必须执行：** 1. 把未完成任务写入
dobralabsAGENTS.mddobralabs/ccos-ratos/AGENTS.md
raiz não carrega a subpasta sozinho: é preciso ir buscar. - **Chegou material bruto** (transcrição, PDF, email exportado): vai pra pasta do projeto certo, e o essencial é destilado no `contexto.md
Benboerba620AGENTS.mdBenboerba620/ai-workspace-hub/AGENTS.md
system/skills/workspace-status.md` + `workspace/review-queue.md` | 只读汇总，不修改判断 | | 升级工作区 | `system/skills/upgrade-workspace.md` | 先预览，确认后只更新受管文件 | | 摄入材料 | `wiki/_schema.md` + `system/integrations/personal-wiki.md`；笔记走 `system/skills/first-ingest.md` 并自动打标签，PDF 走 `system/skills/pdf-ingest.md` | `wiki/` | | 首次股票研究 | `system/skills/first-research.md` + `workspace/research-profile.md` | `output/research/` + 研究偏好 v0.1 | | 后续研究 | `workspace/research-profile.md` + `system/skills/research.md` + 两个知识索引；结束走 `system/skills/research-closeout.md
rookslogAGENTS.mdrookslog/zlibrary-mcp/AGENTS.md
Python side — which is where most of the actual logic lives. **Five real-PDF tests do not run in CI** (issue #85): the repo exceeded its Git LFS budget
bybren-llcAGENTS.mdbybren-llc/story-systems-template/AGENTS.md
Agent (understands intent) ↓ WTFB Agents (craft expertise + authority) ↓ @wtfb/cli via Bash (execution) ↓ Output (PDF, FDX, HTML, validated files) ``` ### Example Interactions | Writer Says | Agent Runs | |-------------|------------| | "Export my script to PDF" | `wtfb
AlekseiULAGENTS.mdAlekseiUL/sprut-agent-kit/AGENTS.md
конфиге) --- ## Skills **Маршрутизация — ВСЕГДА используй skill если он подходит:** - Контент для AI ОПЕРАЦИОНКА (инструкции, PDF, MD) → `methodologist` + `copywriter-agent` - Посты для Telegram/YouTube → `copywriter-agent` - Продающие тексты, воронки, стратегия → `creator-marketing
drpwchenAGENTS.mddrpwchen/paper-fetch/AGENTS.md
where the hard lines are. ## What this tool is A publisher-aware full-text PDF fetcher built as a **route ladder**: open access (Unpaywall + Semantic Scholar + PMC) → official publisher
tam159AGENTS.mdtam159/next-role/backend/AGENTS.md
side endpoint from `.env`. - rendercv renders in a throwaway scratch dir (see `render_resume_pdf` in `tools.py` + `render_scratch.py`): a host `TemporaryDirectory` under `SANDBOX_PROVIDER=local`, a dir inside the remote
adriannoesAGENTS.mdadriannoes/awesome-agentic-ai/AGENTS.md
request to a folder. Prefer the local file over a web summary when a PDF or notebook is in the tree. | Intent | Start | |--------|--------| | Research papers | [papers/README.md](papers/README.md) — theme folders underneath
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.
