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
gitpod-ioAGENTS.md

gitpod

gitpod-io/gitpod/AGENTS.md

Gitpod is a multi-language monorepo for a Kubernetes-based development environment platform. Keep changes focused: identify the component or workflow you are changing and read its local documentation before editing it.

14k3y agoReviewMountCreate a free account to mount
gitpod-ioPipes a download into a shellSkill

cve-mitigation

gitpod-io/gitpod/cve-mitigation/SKILL.md

Scan, triage, and remediate CVEs in the Gitpod monorepo. Use when asked to fix vulnerabilities, update dependencies for security, respond to CVE scan failures, or validate that dependency updates resolve known CVEs. Triggers on "fix CVE", "vulnerability scan", "security update", "dependency CVE", "grype scan", "leeway sbom", "CVE remediation", "update vulnerable dependency", "daily scan failure", "critical vulnerability".

14k3y agoReviewMountCreate a free account to mount
gitpod-ioAGENTS.md

openvscode-server

gitpod-io/openvscode-server/AGENTS.md

This file provides instructions for AI coding agents working with the VS Code codebase. For detailed project overview, architecture, coding guidelines, and validation steps, see the Copilot Instructions.

7 projects use a version of this

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioCLAUDE.md

openvscode-server

gitpod-io/openvscode-server/.claude/CLAUDE.md

../.github/copilot-instructions.md

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioCopilot instructions

openvscode-server

gitpod-io/openvscode-server/.github/copilot-instructions.md

Visual Studio Code is built with a layered architecture using TypeScript, web APIs and Electron, combining web technologies with native app capabilities. The codebase is organized into key architectural layers: The core architecture follows these principles: - Layered architecture - from base, platform, editor, to workbench - Dependency injection - Services are injected through constructor parameters - If non-service parameters are needed, they need to come after the service parameters - Contribution model - Features contribute to registries and extension…

No other project uses it yet

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

accessibility

gitpod-io/openvscode-server/.github/skills/accessibility/SKILL.md

Accessibility guidelines for VS Code features — covers accessibility help dialogs, accessible views, verbosity settings, accessibility signals, ARIA alerts/status announcements, keyboard navigation, and ARIA labels/roles. Applies to both new interactive UI surfaces and updates to existing features. Use when creating new UI or updating existing UI features.

Often used withauthor-contributionsproject-preferenceschat-perf

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

agent-sessions-layout

gitpod-io/openvscode-server/.github/skills/agent-sessions-layout/SKILL.md

Agent Sessions workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agent Sessions workbench layout.

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

author-contributions

gitpod-io/openvscode-server/.github/skills/author-contributions/SKILL.md

Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioDeletes or force-pushesSkill

azure-pipelines

gitpod-io/openvscode-server/.github/skills/azure-pipelines/SKILL.md

Use when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

fix-errors

gitpod-io/openvscode-server/.github/skills/fix-errors/SKILL.md

Guidelines for fixing unhandled errors from the VS Code error telemetry dashboard. Use when investigating error-telemetry issues with stack traces, error messages, and hit/user counts. Covers tracing data flow through call stacks, identifying producers of invalid data vs. consumers that crash, enriching error messages for telemetry diagnosis, and avoiding common anti-patterns like silently swallowing errors.

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

hygiene

gitpod-io/openvscode-server/.github/skills/hygiene/SKILL.md

Use when making code changes to ensure they pass VS Code's hygiene checks. Covers the pre-commit hook, unicode restrictions, string quoting rules, copyright headers, indentation, formatting, ESLint, and stylelint. Run the hygiene check before declaring work complete.

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

sessions

gitpod-io/openvscode-server/.github/skills/sessions/SKILL.md

Agent Sessions window architecture — covers the sessions-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agent Sessions window.

6.2k16mo agoReviewMountCreate a free account to mount
gitpod-ioSkill

tool-rename-deprecation

gitpod-io/openvscode-server/.github/skills/tool-rename-deprecation/SKILL.md

Ensure renamed built-in tool references preserve backward compatibility. Use when renaming a toolReferenceName, tool set referenceName, or any tool identifier. Run on ANY change to tool registration code. Covers legacyToolReferenceFullNames for tools and legacyFullNames for tool sets.

6.2k16mo 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.