brain
01Skill Claude CodeCodex
Use this skill when the task needs durable memory shared across coding-agent harnesses through the external brain CLI and MCP server.
2.2k 25d ago A 1 tokens
original Apache-2.0
2.2kStars on the repository
15Mods indexed here, across every type
25d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown
Skill Claude CodeCodex
Use this skill when a user wants to turn repeated human-approved agent work across Claude Code, Hermes, OpenClaw, Codex, Cursor, or custom .agent/ loops into local artifacts for retrieval, evals, prompt shrinking, and optional future open-weight model/adapters.
2.2k 25d ago A 4 tokens
original Apache-2.0
data-layer
03Skill Claude CodeCodex
Use this skill when the user wants to measure agent activity across Claude Code, Hermes, OpenClaw, Codex, Cursor, OpenCode, Windsurf, Pi, Antigravity, or any custom loop using .agent/.
2.2k 25d ago A 2 tokens
original Apache-2.0
Skill Claude CodeCodex
Follow this loop every time. Jumping straight to "fix" without reproducing is how false fixes ship.
2.2k 25d ago A 3 tokens
original Apache-2.0
Skill Claude CodeCodex
Run this checklist before any deploy. The production deploy itself is gated by a human approval step enforced in protocols/permissions.md.
2.2k 25d ago A 3 tokens
original Apache-2.0
design-md
06Skill Claude CodeCodex
Use this skill when a task touches Google Stitch's DESIGN.md format or the project explicitly references its design system / design tokens. The skill loads only when DESIGN.md exists at the project root (see preconditions above), so general UI / frontend / component work that isn't tied to a DESIGN.md won't trip it.
2.2k 25d ago A 2 tokens
original Apache-2.0
git-proxy
07Skill Claude CodeCodex
Handle git operations consistently. The fences (constraints above) are enforced by the pretoolcall hook; this file tells the agent what good behavior looks like within those fences.
2.2k 25d ago A 3 tokens
original Apache-2.0
Skill Claude CodeCodex
Read constraints and the run checkpoint before assessing a change. Treat deny paths, allowlists, file-count caps, and external-write approvals as hard gates.
2.2k 25d ago A 3 tokens
original Apache-2.0
loop-guard
09Skill Claude CodeCodex
Read current state before spending another attempt. Stop on pause, budget, stagnation, or cancellation decisions and preserve the checkpoint.
2.2k 25d ago A 3 tokens
original Apache-2.0
loop-triage
10Skill Claude CodeCodex
Read the selected loop contract and current checkpoint before reporting. Keep the report bounded and do not mutate the workspace.
2.2k 25d ago A 4 tokens
original Apache-2.0
Skill Claude CodeCodex
Read the contract and checkpoint before reviewing. The deterministic verifier is authoritative; do not turn a checker approval into a test pass.
2.2k 25d ago A 3 tokens
original Apache-2.0
Skill Claude CodeCodex
After every major task or failure, call tools/memoryreflect.py to log what happened. Before important decisions, read the top entries from memory/semantic/LESSONS.md and memory/semantic/DECISIONS.md.
2.2k 25d ago A 2 tokens
original Apache-2.0
skillforge
13Skill Claude CodeCodex
Skill "skillforge" from codejunkie99/agentic-stack, covering skillforge — the skill that creates skills, what good skills look like and self-rewrite hook.
2.2k 25d ago A 2 tokens
original Apache-2.0
tldraw
14Skill Claude CodeCodex
The tldraw MCP server exposes a live canvas at http://localhost:3030. You draw into it; the user watches it fill in. Worthwhile drawings can be snapshotted to disk and recalled in future sessions via this skill's local store (store.py).
2.2k 25d ago A 3 tokens
original Apache-2.0