agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

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.

Worked for most · soon
jaydubya818AGENTS.md

Agentic-KB

jaydubya818/Agentic-KB/AGENTS.md

No summary in the file. Open it to read it.

23mo agoReviewMountCreate a free account to mount
jaydubya818CLAUDE.md

Agentic-KB

jaydubya818/Agentic-KB/CLAUDE.md

(see wiki/private/stuck-on.md locally — plaintext gitignored, encrypted .enc may be committed)_ (see wiki/private/next-milestone.md locally)_ Sensitive content (active interviews, comp, family context, therapy themes, anything you would not put in a public repo) lives under wiki/_private/ and is gated behind a PIN. Plaintext .md files there are gitignored; encrypted .enc blobs may be committed and synced across machines. PIN is read from argv, $AGENTICKBPIN, or interactive prompt. Crypto: AES-256-GCM with PBKDF2 (100k iterations, SHA-256) key derivation. PIN is never persisted. If…

23mo agoReviewMountCreate a free account to mount
jaydubya818Skill

autoresearch

jaydubya818/Agentic-KB/.claude/skills/autoresearch/SKILL.md

Run a bounded autonomous research loop against the Agentic-KB. Given a topic, repeatedly identify gaps, pull web sources, stub them into raw/, INGEST, and re-evaluate until the loop saturates (no new concepts) or hits a hard cap. Use when the user asks to "autoresearch", "deep-dive", "auto-ingest", or "build out the wiki on <topic>" and wants it done without manual round-trips.

23mo agoReviewMountCreate a free account to mount
jaydubya818Skill

defuddle

jaydubya818/Agentic-KB/.claude/skills/defuddle/SKILL.md

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.

Surging+5 new adopters in 4 weeks

60 projects use a version of this

23mo agoReviewMountCreate a free account to mount
jaydubya818Skill

json-canvas

jaydubya818/Agentic-KB/.claude/skills/json-canvas/SKILL.md

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

Surging3 mentions in 2 weeks

63 projects use a version of this

Often used withdefuddleobsidian-cli

23mo agoReviewMountCreate a free account to mount
jaydubya818Skill

obsidian-bases

jaydubya818/Agentic-KB/.claude/skills/obsidian-bases/SKILL.md

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Often used withdefuddleobsidian-cliqmd

23mo agoReviewMountCreate a free account to mount
jaydubya818Skill

obsidian-cli

jaydubya818/Agentic-KB/.claude/skills/obsidian-cli/SKILL.md

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

Surging3 mentions in 2 weeks

80 projects use a version of this

Often used withobsidian-basesdefuddleqmd

23mo agoReviewMountCreate a free account to mount
jaydubya818Skill

obsidian-markdown

jaydubya818/Agentic-KB/.claude/skills/obsidian-markdown/SKILL.md

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

Rising3 mentions in 2 weeks

81 projects use a version of this

Often used withdefuddleobsidian-clifind-skills

23mo agoReviewMountCreate a free account to mount
jaydubya818Reads credentialsSkill

morning-review-daily

jaydubya818/Agentic-KB/skills/morning-review-daily/SKILL.md

Run the Morning Review daily pipeline, append Agentic-KB intelligence to today's daily note, then APPLY the findings — generate promoted pages, persist proposals, draft a synthesis — committing each unit separately.

23mo agoReviewMountCreate a free account to mount
jaydubya818AGENTS.md

Agentic-Pi-Harness

jaydubya818/Agentic-Pi-Harness/AGENTS.md

Guidance for coding agents working in this repository. Governed execution harness for Pi-supervised worker runtimes: a hardened Pi <-> Hermes bridge, versioned execution contracts (v2), persistent run state, KB/Wiki write-policy enforcement, deterministic golden-path replay, and crash-safe artifacts. TypeScript, ESM, Node >= 20.11. All four of typecheck, test, lint, and build must pass before a change is done.

27mo agoReviewMountCreate a free account to mount
jaydubya818CLAUDE.md

Agentic-Pi-Harness

jaydubya818/Agentic-Pi-Harness/CLAUDE.md

Default concise-response mode in this repo: Caveman lite. Use these defaults unless the user asks for more detail: Do not compress away important details for: - governed execution behavior - KB/Wiki policy boundaries - contract/state/event semantics - safety constraints - migration or operational steps - exact commands, paths, IDs, schemas, or failure modes If the user explicitly asks for a detailed explanation, fuller reasoning, or formal wording, expand as needed.

27mo agoReviewMountCreate a free account to mount
jaydubya818AGENTS.md

MissionControl

jaydubya818/MissionControl/AGENTS.md

No summary in the file. Open it to read it.

28mo agoReviewMountCreate a free account to mount
jaydubya818CLAUDE.md

MissionControl

jaydubya818/MissionControl/CLAUDE.md

Frameworks: GSD for new features/modules · Superpowers superpowers:test-driven-development for orchestration logic (agent errors are not recoverable) · See ~/.claude/CLAUDE.md for full guide MissionControl is a Turbo monorepo orchestration platform managing AI agent workflows. The orchestration-server routes agent tasks. Errors here cascade.

28mo agoReviewMountCreate a free account to mount
jaydubya818Skill

ckm:banner-design

jaydubya818/MissionControl/.claude/skills/banner-design/SKILL.md

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.

28mo agoReviewMountCreate a free account to mount
jaydubya818Skill

ckm:brand

jaydubya818/MissionControl/.claude/skills/brand/SKILL.md

Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

Often used withmarketing-ideas

28mo agoReviewMountCreate a free account to mount
jaydubya818Reads credentialsSkill

ckm:design

jaydubya818/MissionControl/.claude/skills/design/SKILL.md

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

28mo agoReviewMountCreate a free account to mount
jaydubya818Skill

ckm:design-system

jaydubya818/MissionControl/.claude/skills/design-system/SKILL.md

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Often used withrevopssite-architecturemarketing-ideas

28mo agoReviewMountCreate a free account to mount
jaydubya818Skill

ckm:slides

jaydubya818/MissionControl/.claude/skills/slides/SKILL.md

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

Often used withmarketing-ideas

28mo agoReviewMountCreate a free account to mount
jaydubya818Skill

ckm:ui-styling

jaydubya818/MissionControl/.claude/skills/ui-styling/SKILL.md

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.

28mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

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 or AGENTS.md?

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.

What is a skill?

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.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.