Skill Claude CodeCodex
Agile Engineering Process (Align-Execute-Prove) methodology with phase planning, test matrices, and evaluation harnesses.
not rated 3 3mo ago A 27 tokens
original MIT
Skill Claude CodeCodex
Reference agent definitions with capability taxonomy for multi-agent orchestration.
not rated 3 3mo ago A 16 tokens
original MIT
Skill Claude CodeCodex
Quick-reference coding standards and backend patterns for consistent development.
not rated 3 3mo ago A 13 tokens
original MIT
Skill Claude CodeCodex
Registry and index of all orchestration command skills.
not rated 3 3mo ago A 15 tokens
original MIT
agent-spawn
77Skill Claude CodeCodex
Use when you need to spawn a specialist sub-agent to handle a specific task domain without polluting the main session context.
not rated 3 3mo ago A 28 tokens
original MIT
Skill Claude CodeCodex
Use when you need to check the current session's context usage and get recommendations for compaction or continuation.
not rated 3 3mo ago A 24 tokens
original MIT
fleet-status
79Skill Claude CodeCodex
Use when you need to check the status of all running agents, workers, and claims in the current fleet.
not rated 3 3mo ago A 25 tokens
original MIT
handoff
80Skill Claude CodeCodex
Use when ending a session and preparing for the next session — creates checkpoint, updates next-session.md, and ensures all PRs are tracked.
not rated 3 3mo ago A 31 tokens
original MIT
Skill Claude CodeCodex
Diagnose and fix build or test failures with minimal targeted changes.
not rated 3 3mo ago A 17 tokens
original MIT
orch-docs
82Skill Claude CodeCodex
Synchronize documentation with code changes.
not rated 3 3mo ago A 10 tokens
original MIT
orch-e2e
83Skill Claude CodeCodex
Generate and run end-to-end tests for critical flows.
not rated 3 3mo ago A 15 tokens
original MIT
orch-handoff
84Skill Claude CodeCodex
Generate a session wrap summary documenting state, decisions, and recommended next steps.
not rated 3 3mo ago A 18 tokens
original MIT
orch-panel
85Skill Claude CodeCodex
Invoke a Panel of Experts review on any artifact — code, architecture, plans, repos, or documentation.
not rated 3 3mo ago A 23 tokens
original MIT
orch-plan
86Skill Claude CodeCodex
Create an approval-gated implementation plan with phased tasks and acceptance criteria.
not rated 3 3mo ago A 16 tokens
original MIT
Skill Claude CodeCodex
Dead code cleanup and refactoring without behavior changes.
not rated 3 3mo ago A 13 tokens
original MIT
Skill Claude CodeCodex
Research top repos for a user-supplied topic with expert panel evaluation and presentation packaging.
not rated 3 3mo ago A 21 tokens
original MIT
orch-review
89Skill Claude CodeCodex
Trigger code review workflow with risk detection and reviewer routing.
not rated 3 3mo ago A 13 tokens
original MIT
orch-status
90Skill Claude CodeCodex
Review current operational state and surface blockers, constraints, or pending actions.
not rated 3 3mo ago A 16 tokens
original MIT
orch-tasks
91Skill Claude CodeCodex
List open tasks with priorities, status, and acceptance criteria.
not rated 3 3mo ago A 15 tokens
original MIT
orch-tdd
92Skill Claude CodeCodex
Use when implementing a feature via test-driven development - write a failing test first, get to green with the smallest correct change, then refactor. Enforces vertical slice shape and red-commit-hash evidence.
not rated 3 3mo ago A 46 tokens
original MIT
orch-verify
93Skill Claude CodeCodex
Capture verification evidence for the current task by running tests and logging results.
not rated 3 3mo ago A 17 tokens
original MIT
Skill Claude CodeCodex
Use when you want to run the ECC learning loop (eval-harness + pattern-extractor) over current session evidence to extract behavioral patterns and update MEMORY.md.
not rated 3 3mo ago A 36 tokens
original MIT
quality-gate
95Skill Claude CodeCodex
Use when you need to check if current work meets quality thresholds before proceeding to the next phase or merging.
not rated 3 3mo ago A 25 tokens
original MIT
scope-lock
96Skill Claude CodeCodex
Use when you want to lock the session to a specific scope description, injecting it into purpose-gate context and optionally blocking out-of-scope tool calls.
not rated 3 3mo ago A 34 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: