One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
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.
AgriciDanielReads credentialsCLAUDE.mdAgriciDaniel/claude-code-essentials-vs-code/templates/CLAUDE.md
This is an example, not detected project configuration. Replace the stack, commands, paths, and conventions with those verified in your repository before using this file. Record actual dependency versions from its manifests/lockfiles.
AgriciDanielAGENTS.mdAgriciDaniel/anti-slop/anti-slop-brain/AGENTS.md
The canonical agent entrypoint is SKILL.md; this file exists for agent runtimes that load project-level AGENTS.md instructions. - Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes. - A scaffold is not a finished brain. - Domain-specific claims require dated trustworthy sources. - Research evidence must be recorded in references/source-ledger.json. - Adapter completion must be recorded in references/adapter-manifest.json. - Preserve .raw/ as immutable source material. - Keep Obsidian wiki/, CODEX.md, dashboards, canvases, frontmatter, wikilinks, graph hygiene, and source…
AgriciDanielCLAUDE.mdAgriciDaniel/anti-slop/anti-slop-brain/CLAUDE.md
Claude-specific note: this file is persistent project context, not an enforcement layer. Release readiness is enforced by scripts/audit_brain.py and scripts/package_release.py.
AgriciDanielSkillAgriciDaniel/anti-slop/anti-slop-brain/SKILL.md
Scaffold and operate Anti-Slop Brain, a source-cited Obsidian brain for detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection. Use when the user says "anti-slop-brain", "Anti-Slop Brain", "create a detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection brain", "import sources", "synthesize plan", "render report", or wants a persistent vault-backed operating system for detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection.
AgriciDanielCLAUDE.mdAgriciDaniel/claude-music/CLAUDE.md
AI music production skill for Claude Code, powered by ACE-Step 1.5.
AgriciDanielAGENTS.mdAgriciDaniel/meowmeow/AGENTS.md
This file is the agent-readable contract for this repo. If your tooling loads AGENTS.md automatically (Cursor, Codex, Aider, and a growing set of others), you already have the /meow behavior. When the user says /meow, do not ask what they mean. Inspect your own previous response and pick the action that fits: Same signal, different meaning per context. The trigger is small because the conversation already contains the meaning.
AgriciDanielCursor ruleAgriciDaniel/meowmeow/.cursor/rules/meow.mdc
When the user says /meow, classify the previous assistant response and act on it without asking for clarification.
AgriciDanielReads credentialsAGENTS.mdAgriciDaniel/youtube-scout/AGENTS.md
Portable instructions for any coding agent (Codex, Gemini, Cursor, and others) working in this repository. Claude Code reads CLAUDE.md, which says the same thing. A single-script Claude Code skill. scripts/scout.py searches YouTube Data API v3 for a topic, enriches each video, and writes an .xlsx research workbook. SKILL.md is the runtime contract the agent follows when a user types /scout.
AgriciDanielReads credentialsCLAUDE.mdAgriciDaniel/youtube-scout/CLAUDE.md
Claude Code skill: /scout <topic> turns one topic into a ranked YouTube research workbook. Read SKILL.md for the runtime contract and README.md for the product view. - Source of truth is this checkout. ~/.claude/skills/scout/ is an installed copy; after changing scripts/scout.py or SKILL.md, run ./install.sh to refresh it. - Quality gate: python -m pytest (offline, fixtures under tests/fixtures/) and ruff check .. Every behaviour change ships with a test. - Never commit API keys, .env files, generated workbooks, downloads, or…
AgriciDanielReads credentialsSkillAgriciDaniel/youtube-scout/SKILL.md
Scout a topic on YouTube. Searches YouTube Data API v3 for the most relevant videos, ranks them by views (or engagement, likes, recency, momentum, breakout), and writes a research workbook in the OWT-Social-Ads layout with Videos, Channels, and Summary sheets, plus optional Comments and Transcripts (hooks, replay hotspots) sheets. Can also append into an existing sheet. Use when the user says "scout <topic>", wants a spreadsheet of top YouTube videos on a topic, wants creator or hook research, or wants YouTube rows added to their social ads sheet.
AgriciDanielAGENTS.mdAgriciDaniel/fablesecondbrain/AGENTS.md
The canonical agent entrypoint is SKILL.md; this file exists for agent runtimes that load project-level AGENTS.md instructions. - Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes. - A scaffold is not a finished brain. - Domain-specific claims require dated trustworthy sources. - Research evidence must be recorded in references/source-ledger.json. - Adapter completion must be recorded in references/adapter-manifest.json. - Preserve .raw/ as immutable source material. - Keep Obsidian wiki/, CODEX.md, dashboards, canvases, frontmatter, wikilinks, graph hygiene, and source…
AgriciDanielCLAUDE.mdAgriciDaniel/fablesecondbrain/CLAUDE.md
Claude-specific note: this file is persistent project context, not an enforcement layer. Release readiness is enforced by scripts/audit_brain.py and scripts/package_release.py. Master copy: wiki/meta/CONVENTIONS.md (restore from there if a brainstein upgrade overwrites this file). - Three layers: .raw/ immutable sources with sha256 manifest; wiki/ knowledge; this file the agent contract. Never edit anything under .raw/. - Read order for any session: wiki/hot.md, then wiki/index.md, then the relevant _index.md hub, then the note. - Every wiki page carries flat YAML frontmatter: type,…
AgriciDanielSkillAgriciDaniel/fablesecondbrain/SKILL.md
Scaffold and operate Fable 5 Brain, a source-cited Obsidian brain for Claude Fable 5 model and Claude Code harness ai operations and source-cited best practices. Use when the user says "fable-5-brain", "Fable 5 Brain", "create a Claude Fable 5 model and Claude Code harness ai operations and source-cited best practices brain", "import sources", "synthesize plan", "render report", or wants a persistent vault-backed operating system for Claude Fable 5 model and Claude Code harness ai operations and source-cited best practices.
AgriciDanielReads credentialsSkillAgriciDaniel/lipnardo/skills/lipnardo/SKILL.md
Generate AI avatar talking-head videos using HeyGen API. Single videos, multi-scene studio compositions, batch personalization from CSV/JSON, template variable injection, photo-to-avatar pipeline, video translation with lip-sync, Starfish TTS, credit estimation, and asset management. Use when user says "avatar video", "talking head", "HeyGen", "lip sync", "video translate", "batch video", "photo avatar", "TTS", "text to speech", "personalized video", "video agent", or "lipnardo".
AgriciDanielSkillAgriciDaniel/all-profile/skills/all-profile/SKILL.md
Audit, write, and update social profiles across LinkedIn, YouTube, Instagram, TikTok, and X. Covers bios, headlines, About sections, YouTube channel descriptions, links, evidence-backed positioning, and verification of approved live edits. Use for one profile or cross-platform consistency, not post or video descriptions, content calendars, account-ban investigations, or repository descriptions.
AgriciDanielReads credentialsAGENTS.mdAgriciDaniel/gatekeeper/AGENTS.md
Read SKILL.md, then README.md, then the rulebook you are touching in gates/. - Code owns the workflow. Jev answers only the semantic questions a rule cannot. - Thresholds live in rulebooks, never in Python. Move one only with a bench report over hand-reviewed labels, and bump the rulebook version. - Gatekeeper decides who handles work and whether it may proceed. It never takes outside actions (send, publish, deploy, spend) itself. - Hooks must fail open and must never break a…
AgriciDanielCLAUDE.mdAgriciDaniel/gatekeeper/CLAUDE.md
No summary in the file. Open it to read it.
AgriciDanielReads credentialsSkillAgriciDaniel/gatekeeper/SKILL.md
Rule-driven decision gates for anything that needs a verdict before it proceeds: agent selection, routing, triage, approvals. Each gate is a YAML rulebook: deterministic hard rules decide what code can decide, Jev (TypeSafe System One) answers the semantic questions as typed Choice, Noul, or Score judgments, and confidence bands turn answers into allow, route, suggest, confirm, escalate, or block. Rosters come from installed Claude Code agents and skills or from a JSON index, with rollup by group. Runs as Claude Code hooks in shadow, advise, or enforce mode (ships in shadow). Use for "/gatekeeper", "gatekeeper", "which agent should handle this", "why was that blocked", "tune the gate", "bench the gate", "write a new gate", "add a rule", "is the gate healthy", or "gatekeeper doctor".
AgriciDanielAGENTS.mdAgriciDaniel/sync/AGENTS.md
The canonical agent entrypoint is SKILL.md; this file exists for agent runtimes that load project-level AGENTS.md instructions. - Do not call this brain market-ready unless scripts/audit_brain.py --require market-ready passes. -…
AgriciDanielCLAUDE.mdAgriciDaniel/sync/CLAUDE.md
Claude-specific note: this file is persistent project context, not an enforcement layer. Release readiness is enforced by scripts/audit_brain.py and scripts/package_release.py.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
