Skill Claude CodeCodex
Respond to an automated reviewer's findings on the current feature PR — a narrow, headless responder. Triages each reviewer finding into Clear / Ambiguous / Complex / Out-of-PRD-Scope, then acts — fixes the cause and pushes (diff-only) for Clear, posts one in-thread reply for the rest. Skips findings it already…
Skill Claude CodeCodex
One-time setup of a project as a harness ENVIRONMENT — the Software 3.0 half that follows context-specs add. Generates the project-specific artifacts an LLM must read the repo to write (AGENTS.md, bootstrap-worktree.sh, local-checks.sh), installs the project-owned /intent, seeds the Expert (long-term memory) skeleton…
Skill Claude CodeCodex
This project's long-term memory — how to run, validate, and extend it; its architecture, patterns, hard invariants, worked examples, and current decisions/direction. Consult when planning a feature, validating a spec, implementing a slice, or writing intent for this project. Routing table below points to one small…
Skill Claude CodeCodex
Patch the code so scripts/local-checks.sh passes, after /implement-mainspec — a narrow post-implement polish specialist. Reads the (remediation-rich) check failures, fixes the underlying cause, never silences a check, re-verifies, and commits. Invoked headless by the dispatcher's two-strike local-checks gate; the…
Skill Claude CodeCodex
Update the project's long-term memory after a merge to main. Reads the merged diff and reconciles the current memory — adding, editing, and deleting Expert reference files — then drafts candidate lints and AGENTS.md pointers. Opens a reviewable learn/ PR, or prints "nothing to learn" and exits if the merge produced no…
Skill Claude CodeCodex
Evaluate a PR the harness produced — walk the change, run the system together, and build a firm understanding before you merge it. Use after the harness hands a converged PR to you for review (the "Ready for your review" comment), or any time you want to deeply review an agent-authored PR. The human-attentive skill at…
Skill Claude CodeCodex
The harness concierge for improving a project's context — the human-in-the-loop expert on every context lever (the codebase's own shape, AGENTS.md, the Expert long-term memory, /intent, local-check lints) and on STUCK forensics. Use to resolve a STUCK PR (diagnosis-first), to improve any lever ("improve long-term…
Skill Claude CodeCodex
Turn an open-ended idea into a PRD plus a runnable definition of done. Use when a developer wants to start a new feature, "file a PRD", "spec out" or "scope" an idea, think through what to build, or kick off the harness for a piece of work. Produces prds/ /prd.md + an executable prds/ /run-prd-test.sh on a prd/ /…
Skill Claude CodeCodex
Resolve the outcome of context-specs update — walk every file where your edits and the new upstream version disagree, and decide keep / take / merge / customize with the consequence of each spelled out. Use after context-specs update reports conflicts or semantic reviews, or any time your harness has unresolved…
Skill Claude CodeCodex
One-time, guided setup of a standalone LLM-maintained wiki — a Karpathy "LLM Wiki" style knowledge base for a problem domain and your general architecture best practices. Scaffolds an external wiki vault (its own git repo) with /ingest, /query, /lint commands and a conventions doc. Use when a developer wants to start…
Skill Claude CodeCodex
Implements a mainspec end-to-end by delegating each slice to a slice-implementer subagent in dependency order, committing to feature/ directly. Agent-first — invoked headless by the harness dispatcher with the feature slug. No human-in-the-loop, no approval gates.
Skill Claude CodeCodex
Implements a single slice with unit tests and a Reflect step. Agent-first — invoked by the slice-implementer subagent (under implement-mainspec). No human-in-the-loop.
Skill Claude CodeCodex
Reads a PRD (prds/ /prd.md) plus its executable run-prd-test.sh (and any helper artifacts under prds/ /), grounds them in codebase research, and produces specs/ /mainspec.md plus dependency-ordered slices. Encodes the runner as a slice success criterion so implementation completion implies ./prds/ /run-prd-test.sh…
Skill Claude CodeCodex
Validates a mainspec and its slices via 3-subagent consensus plus expert review, then applies impactful fixes directly to the spec files. No human-in-the-loop summary or approval — agent-first. Touches specs/ /.validated as its final committed action.