
Add or refine diagrams in documentation, especially Mermaid workflow diagrams in apps/docs. Use when a docs page explains actor handoffs, phase gates, failure paths, state transitions, or multi-step flows that are clearer as a diagram.
Run Ralph against either the full repo queue or tasks linked to one design doc, with injected task/spec/queue context for Codex or Claude runtimes.
Release a new lockstep version of tx to GitHub and npm with preflight validation, workflow monitoring, and registry verification.
Refresh bundled tx Claude Code and Codex skills in a project from the canonical tx source without manual copy and paste.
Internal closed-loop skill: drive CLI/API/MCP to 100% shape parity (same service methods) AND behaviour parity (same response shapes). Uses ESLint rules tx/require-surface-parity + tx/interface-parity. NOT shipped to tx users.
Generate a system-level design document via `tx doc add design`. Covers cross-cutting architecture, service boundaries, data flows, scalability, and deployment topology. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Use for system-wide or multi-domain designs rather than feature-scoped subsystem docs.
Configure gates, guards, labels, verification, and retrospectives for bounded autonomy. Use when working in Claude Code and the user needs tx commands from this area.
Profile all test files to find slow, hanging, or failing tests. Use when tests seem slow or when vitest hangs.
Inspect graph anchors plus supporting utility and usage commands. Use when working in Claude Code and the user needs tx commands from this area.
Operate workers, daemons, coordinators, cycle scans, and hook installation paths. Use when working in Claude Code and the user needs tx commands from this area.
Implement and verify design doc invariants by annotating tests and source code with [INV-*] / @spec tags, then driving tx spec coverage from BUILD toward HARDEN (100% FCI). Works with any design doc that has an invariants block.
Export, import, migrate, hydrate, and compact task state and sync artifacts. Use when working in Claude Code and the user needs tx commands from this area.
Add or refine diagrams in documentation, especially Mermaid workflow diagrams in apps/docs. Use when a docs page explains actor handoffs, phase gates, failure paths, state transitions, or multi-step flows that are clearer as a diagram.
Generate a detailed design document via `tx doc add design`. Covers architecture, interfaces, data model, invariants, failure modes, verification, and testing strategy. References plan via file path instead of embedding. Plan lives in ~/.codex/plans/<name>.md. Reads companion PRD automatically to map EARS requirements to invariants. Output lands in specs/design/<name>.md.
Refresh bundled tx Claude Code and Codex skills in a project from the canonical tx source without manual copy and paste.
Cut a lockstep tx release with enforced preflight validation, workflow monitoring, and npm verification. Use when bumping versions, tagging releases, repairing partial publishes, or checking publish readiness.
Internal closed-loop skill: drive CLI/API/MCP to 100% shape parity (same service methods) AND behaviour parity (same response shapes). Uses ESLint rules tx/require-surface-parity + tx/interface-parity. NOT shipped to tx users.
Work the main tx queue: initialize, create tasks, inspect work, claim tasks, and complete them. Use when working in Codex and the user needs tx commands from this area.
Configure gates, guards, labels, verification, and retrospectives for bounded autonomy. Use when working in Codex and the user needs tx commands from this area.
Store, recall, search, and relate memory documents, learnings, and task context. Use when working in Codex and the user needs tx commands from this area.
Send agent messages, acknowledge inbox items, and persist shared context pins. Use when working in Codex and the user needs tx commands from this area.
Inspect queue health, diagnostics, dashboards, run traces, and recent failures. Use when working in Codex and the user needs tx commands from this area.
Export, import, migrate, hydrate, and compact task state and sync artifacts. Use when working in Codex and the user needs tx commands from this area.
Operate workers, daemons, coordinators, cycle scans, and hook installation paths. Use when working in Codex and the user needs tx commands from this area.
Guide for working with tx task management. Use when picking up tasks, completing work, or managing dependencies.
Build a verification script that defines "done" for a parent task or project phase. Creates a .sh script and attaches it via tx auto verify set.
Implement and verify design doc invariants by annotating tests and source code with [INV-*] / @spec tags, then driving tx spec coverage from BUILD toward HARDEN (100% FCI). Works with any design doc that has an invariants block.
Auto-annotate existing tests and source code with [INV-*] / @spec tags by reading all spec gaps, understanding each invariant, and matching them to existing test assertions. Optionally creates missing tests too. Drives FCI from 0% toward 100%.
Run Ralph against either the full repo queue or tasks linked to one design doc, with injected task/spec/queue context for Codex or Claude runtimes.
Link tasks to paired PRD/design specs, export all open work to markdown, and keep Ralph-style loops moving by creating tasks, subtasks, and dependency updates through tx primitives.
Turn a design spec into an explicit tx task graph with `tx decompose`, then refine the graph using normal tx task and dependency primitives.
Refresh bundled tx Claude Code and Codex skills in a project from the canonical tx source without manual copy and paste.
Run tests with context-efficient output. Hides passing test output, shows ONLY failures. Use when running tests, checking if tests pass, or verifying changes. Also detects flaky tests.
Generate a system-level design document via `tx doc add design`. Covers cross-cutting architecture, service boundaries, data flows, scalability, and deployment topology. References plan via file path instead of embedding. Plan lives in ~/.codex/plans/<name>.md. Use for system-wide or multi-domain designs rather than feature-scoped subsystem docs.
Auto-annotate existing tests and source code with [INV-*] / @spec tags by reading all spec gaps, understanding each invariant, and matching them to existing test assertions. Optionally creates missing tests too. Drives FCI from 0% toward 100%.
Turn a design spec into an explicit tx task graph with `tx decompose`, then refine the graph using normal tx task and dependency primitives.
Generate a system overview spec via `tx doc add overview`. Produces an architectural overview covering problem, scope, components, data flows, and non-goals. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Output lands in specs/<name>.md with tx-managed frontmatter.
Run Ralph against either the full repo queue or tasks linked to one design doc, with injected task/spec/queue context for Codex or Claude runtimes.
Model blockers, parent-child relationships, and shared group context. Use when working in Codex and the user needs tx commands from this area.
Link tasks to paired PRD/design specs, export all open work to markdown, and keep Ralph-style loops moving by creating tasks, subtasks, and dependency updates through tx primitives.
Run a tx cycle scan — sub-agent swarm for automated codebase issue discovery. Use when the user mentions "cycle", "scan", or "find issues".
Create, patch, lint, discover, trace, and complete docs-first specs. Use when working in Claude Code and the user needs tx commands from this area.
Store, recall, search, and relate memory documents, learnings, and task context. Use when working in Claude Code and the user needs tx commands from this area.
Inspect graph anchors plus supporting utility and usage commands. Use when working in Codex and the user needs tx commands from this area.
Build a verification script that defines "done" for a parent task or project phase. Creates a .sh script and attaches it via tx auto verify set.
Implement and verify design doc invariants by annotating tests and source code with [INV-*] / @spec tags, then driving tx spec coverage from BUILD toward HARDEN (100% FCI). Works with any design doc that has an invariants block.
Inspect queue health, diagnostics, dashboards, run traces, and recent failures. Use when working in Claude Code and the user needs tx commands from this area.
Send agent messages, acknowledge inbox items, and persist shared context pins. Use when working in Claude Code and the user needs tx commands from this area.
Create, patch, lint, discover, trace, and complete docs-first specs. Use when working in Codex and the user needs tx commands from this area.
Model blockers, parent-child relationships, and shared group context. Use when working in Claude Code and the user needs tx commands from this area.
Work the main tx queue: initialize, create tasks, inspect work, claim tasks, and complete them. Use when working in Claude Code and the user needs tx commands from this area.
Link tasks to paired PRD/design specs, export all open work to markdown, and keep Ralph-style loops moving by creating tasks, subtasks, and dependency updates through tx primitives.
Generate a detailed Product Requirements Document via `tx doc add prd`. Uses EARS requirement syntax with traceable IDs, acceptance criteria, and non-functional requirements. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Designed to be created alongside a companion `/design-doc`. Output lands in specs/prd/<name>.md.
Generate a detailed Product Requirements Document via `tx doc add prd`. Uses EARS requirement syntax with traceable IDs, acceptance criteria, and non-functional requirements. References plan via file path instead of embedding. Plan lives in ~/.codex/plans/<name>.md. Designed to be created alongside a companion `design-doc`. Output lands in specs/prd/<name>.md.
Generate a detailed Product Requirements Document via `tx doc add prd`. Uses EARS requirement syntax with traceable IDs, acceptance criteria, and non-functional requirements. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Designed to be created alongside a companion `/design-doc`. Output lands in specs/prd/<name>.md.
Generate a system overview spec via `tx doc add overview`. Produces an architectural overview covering problem, scope, components, data flows, and non-goals. References plan via file path instead of embedding. Plan lives in ~/.codex/plans/<name>.md. Output lands in specs/<name>.md with tx-managed frontmatter.
Generate a system overview spec via `tx doc add overview`. Produces an architectural overview covering problem, scope, components, data flows, and non-goals. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Output lands in specs/<name>.md with tx-managed frontmatter.
Auto-annotate existing tests and source code with [INV-*] / @spec tags by reading all spec gaps, understanding each invariant, and matching them to existing test assertions. Optionally creates missing tests too. Drives FCI from 0% toward 100%.
Generate a detailed design document via `tx doc add design`. Covers architecture, interfaces, data model, invariants, failure modes, verification, and testing strategy. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Reads companion PRD automatically to map EARS requirements to invariants. Output lands in specs/design/<name>.md.
Generate a detailed design document via `tx doc add design`. Covers architecture, interfaces, data model, invariants, failure modes, verification, and testing strategy. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Reads companion PRD automatically to map EARS requirements to invariants. Output lands in specs/design/<name>.md.
Turn a design spec into an explicit tx task graph with `tx decompose`, then refine the graph using normal tx task and dependency primitives.
Debug Claude Code hook artifacts. Use when investigating why ralph failed, what hooks fired, what was blocked, or reviewing hook behavior for a run.
Run a tx cycle scan — sub-agent swarm for codebase issue discovery. Use when the user explicitly mentions "cycle". Do NOT use Claude Code teams (TeamCreate/SendMessage) for this — use tx cycle CLI instead.