Agent
Spawn after a work phase settles or when knowledge needs maintenance: pass work refs, changed files, and target repos. Mines decisions, maintains existing docs (delete stale, reorganize misplaced), writes updates into the right knowledge layers, commits each touched repo without pushing, and reports contradictions and…
Agent
Spawn to refactor a documentation tree's structure (KB, .context/, docs/, design/): pass the target root. Splits, merges, renames, and repairs cross-references; returns changed paths and flagged content issues. Never decides content truth.
Agent
Mine conversation history for decisions, rejected alternatives, and constraints.
Agent
General-purpose subagent.
Skill Claude CodeCodex
Investigate and engage concurrently: don't block on evidence before surfacing your read.
Skill Claude CodeCodex
Load when turning intent into an executable goal for an agent, spawn, work item, experiment, or handoff. Use to define outcome, evidence, constraints, anti-goals, stop conditions, and reporting shape before work begins.
Skill Claude CodeCodex
Use when grilling should be grounded primarily in project artifacts. Loads /grill, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.
Skill Claude CodeCodex
Use when grilling should be grounded in evidence. Loads /grill, then checks the plan, terms, and assumptions against project artifacts first and primary sources when needed.
Skill Claude CodeCodex
Use in conversation to stress-test a plan or direction. Interviews the human branch by branch, sharpens terminology, challenges assumptions, and asks the next high-leverage question with a recommended answer.
Skill Claude CodeCodex
Produce a transition brief and launch command for the user's next interactive primary.
Skill Claude CodeCodex
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
Skill Claude CodeCodex
Use before acting on human instructions: separate what they said from what they meant.
Skill Claude CodeCodex
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Skill Claude CodeCodex
Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.
Skill Claude CodeCodex
Use when validating markdown links or Mermaid diagrams.
Skill Claude CodeCodex
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
Skill Claude CodeCodex
Always load on agents that make durable source changes: keep colocated agent-facing knowledge synchronized with the source.
Skill Claude CodeCodex
User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.
Skill Claude CodeCodex
Use when recovering decisions or context from conversation history: session log navigation, transcript delegation.
Skill Claude CodeCodex
Use when establishing shared vocabulary: resolve terminology early, one name per concept, vocab files as record.
Skill Claude CodeCodex
Use when a workspace has changes from other agents: safe orientation, preserving unfamiliar files.
Skill Claude CodeCodex
Load when building a static HTML artifact: single page or multi-page site to make structured information explorable through layout and navigation.
Skill Claude CodeCodex
Anchor work in a work item: artifacts on disk, not in context.
Skill Claude CodeCodex
Use when orienting in an unfamiliar area: fans out parallel explorers across code, knowledge, and history, then synthesizes one orientation map.