Instructions file CodexOpenCode
Instructions for try-works/recursive-mode, covering agents.md and recursive-mode bridge.
Instructions file CodexOpenCode
Instructions for try-works/recursive-mode, covering agents.md and recursive-mode bridge.
Command
Command "check-reusable-repo-hygiene" from try-works/recursive-mode, covering check-reusable-repo-hygiene, usage and what it checks.
Command
Command "recursive-closeout" from try-works/recursive-mode, covering recursive-closeout (prompt template), usage pattern, script (recommended), what it does and preview url capture.
Command
Command "recursive-init" from try-works/recursive-mode, covering recursive-init (prompt template), usage pattern, script (recommended), what it does and output.
Command
Lock recursive artifact: [run-id] [artifact].
Command
Generate a recursive review bundle for run phase 03.5 using the canonical bundle format.
Command
Command "recursive-status" from try-works/recursive-mode, covering recursive-status (prompt template), usage pattern, script (recommended), what it shows and example output shape.
Command
Record a subagent action for run phase so the controller can verify it against real files and recursive artifacts.
Command
Run recursive-mode smoke tests [quick|full|subagent] [python|powershell|mixed].
Skill Claude CodeCodex
Use when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".
Skill Claude CodeCodex
Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
Skill Claude CodeCodex
Use when recursive-mode work needs a canonical delegated-review or audit handoff. Generates reproducible review bundles for Phase 3.5 code review, test review, or other delegated checks using the repo review-bundle scripts.
Skill Claude CodeCodex
Use when recursive-mode needs to route delegated audit, review, or bounded implementation work through external transports, CLIs, and models while preserving controller verification and fallback behavior.
Skill Claude CodeCodex
Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs. Use when the user wants help creating a plan, spec, scope, or requirements for work that does not yet have a run, especially prompts like "create a plan", "help me plan", "create a spec", "write requirements", or similar derivatives.
Skill Claude CodeCodex
Use when recursive-mode work may benefit from delegated audit, review, or bounded implementation support. This skill prioritizes analyst, planner, code-reviewer, memory-auditor, tester, and implementer roles, with mandatory self-audit fallback when subagents are unavailable.
Agent
Use this agent for recursive-mode audit and review work after implementation or before lock. The reviewer must reconcile upstream artifacts, git diff, requirements, plan, tests, and code quality before returning a grounded PASS/FAIL style verdict.
Agent
Use this agent when implementing a single sub-phase from a recursive-mode plan. The agent should receive the full sub-phase text, current codebase context, and implement the feature with TDD discipline.
Skill Claude CodeCodex
Use when implementing any code in recursive-mode Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first. Trigger phrases: "implement this", "add feature", "fix bug", "write a failing test", "TDD".
Skill Claude CodeCodex
Use after completed recursive-mode runs accumulate to extract durable experiential memory into /.recursive/memory/, then load it for later runs through the canonical loader.
Skill Claude CodeCodex
Use when starting any recursive-mode requirement to set up an isolated git worktree. Required before implementation phases: create an isolated workspace, verify a clean baseline, and keep main/master clean.