ralph-wiggum
49Skill Claude CodeCodex
Run Ralph Wiggum autonomous coding loops where each fresh agent iteration implements, verifies, commits, and records one task.
6 6d ago A 30 tokens
original MIT
Skill Claude CodeCodex
A single Rust binary that filters and summarises command output before it hits the LLM context. 80% fewer tokens on common dev commands, <10ms overhead, 100+ commands. Apache-2.0. Directly serves token-reduction doctrine.
6 6d ago C 63 tokens
original MIT
plan
51Skill Claude CodeCodex
Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's .hermes/plans/ directory, and do not execute the work.
6 6d ago A 35 tokens
copy · 88% MIT
Skill Claude CodeCodex
Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.
6 6d ago A 46 tokens
copy · 88% MIT
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks. Dispatches fresh delegatetask per task with two-stage review (spec compliance then code quality).
6 6d ago A 32 tokens
copy · 86% MIT
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
6 6d ago A 33 tokens
copy · 94% MIT
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
6 6d ago A 33 tokens
copy · 94% MIT
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.
6 6d ago A 36 tokens
copy · 91% MIT
spike
57Skill Claude CodeCodex
Throwaway experiments to validate an idea before build.
6 6d ago A 13 tokens
copy · 94% MIT
Skill Claude CodeCodex
Scrape TypeScript, React, Next.js, Nuxt, Vue SPA sites. Know when to use raw HTML fetch vs browser automation.
6 6d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Delegate coding tasks to external autonomous AI coding CLI agents — Claude Code, Codex, OpenCode, and Kanban+Codex lane patterns. Covers install, auth, one-shot tasks, interactive sessions, PR reviews, parallel worktrees, and reconciliation.
6 6d ago A 55 tokens
original MIT
Skill Claude CodeCodex
Implementation and troubleshooting of the Cognitive Memory (Cognify) system in Hermes Agent.
6 6d ago A 21 tokens
original MIT