Ancienttwo

repo-harness-prd

Generates an AI-implementation-friendly PRD from a product idea into plans/prds/, with tiered sections, evidence rules, and sprint-consumable structure.

repo-harness-architecture

Resolves repo-harness architecture drift requests and updates architecture docs or diagrams without running full init, migrate, or upgrade.

Full repo-harness workflow orchestrator. Reads repo state, drafts a plan, self-reviews twice, executes the approved plan, runs review/check gates, and delegates final PR closeout to repo-harness-ship.

repo-harness-check

Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.

repo-harness-goal

Goal-mode entrypoint for Codex and Claude native /goal sessions. Requires detailed PRD or Sprint context before starting bounded long-running execution.

repo-harness-gptpro-setup

Guides GPT Pro local setup for repo-harness by configuring Oracle-first gptpro_browser ChatGPT Web consults and gptpro_mcp ChatGPT Connector MCP sidecar access with verification, auth, tunnel, runtime, and API-billing boundaries.

repo-harness-gptpro

Direct GPT Pro consult facade for repo-harness. Use when the user asks for repo-harness:gptpro, GPT Pro advice, GPT Pro review, gptpro consult, or continuing/opening a GPT Pro browser session through the Oracle-first local ChatGPT Web browser provider.

Code & Development Featured

repo-harness-ship

Final repo-harness closeout workflow. Runs review/check gates, commits finished contract worktrees, pushes codex branches, and creates GitHub PRs by default.

repo-harness-sprint

Program-level sprint planning and execution entrypoint. Uses upper-layer PRDs from plans/prds/ when present, writes ordered sprint backlogs in plans/sprints/, expands contract rows with $think into plan/contract/worktree flow, and keeps inline rows inside the sprint backlog or active plan checklist.

Code & Development Featured

codex-review

Get an independent cross-model code review from OpenAI Codex (a different vendor's model) on the current review scope: branch diff plus staged, unstaged, and untracked working tree changes. A different training distribution has non-overlapping blind spots, so Codex catches spec ambiguity, missing edge cases, and fake tests that Claude's self-review cannot see. Use before merging, after a tricky change, or for a debug second opinion. Triggers: 'codex review', 'second opinion', 'cross review', 'outside voice', '让 codex 审', '找外部意见', '二审'.

repo-harness-plan

Interactive planning entrypoint for repo-local agentic development work. Produces an approved plan before implementation, and reviews an existing plan across product, engineering, design, and DevEx dimensions.

repo-harness-repair

Repairs a broken current harness, including task sync, hook routing, handoff, context-map, policy, helper, and generated/runtime drift.

repo-harness

Route explicit repo-harness setup, planning, execution, verification, and handoff actions through deterministic repository state.

repo-harness-capability

Adds or syncs explicit repo-local capability boundaries without running full repo-harness init, migrate, or upgrade.

repo-harness-deploy

Checks deploy and private operations configuration for an repo-harness harness without publishing or deploying.

repo-harness-handoff

Prepares or resumes Codex handoff packets for long-task rollover without running the full workflow check surface.

repo-harness-init

Installs or refreshes the repo-harness workflow in an existing repository. Adds hooks, docs/spec.md, tasks, plans, .ai/context, .ai/harness, helpers, and policy without creating an application stack.

repo-harness-migrate

Migrates older Claude/Codex workflow repos to the current tasks-first harness while preserving or archiving user-authored docs and hooks.

Code & Development Solid

repo-harness-review

Reviews an existing repo-harness plan across product, engineering, design, and DevEx dimensions before implementation or release follow-through.

repo-harness-scaffold

Branch command that creates a new project or module scaffold from the repo-harness plan catalog A-K, then attaches the repo-local workflow harness.

repo-harness-upgrade

Refreshes an already-installed repo-harness harness using manifest-owned upgrade actions from assets/workflow-contract.v1.json.

repo-harness-chatgpt

Canonical rule owner for repo-harness ChatGPT integration -- Oracle-first browser/GPT Pro consult and continuation, MCP Connector setup, MCP bridge planning handoff, and Connector invocation read-back evidence.

Code & Development Solid

repo-harness-cross-review

Independent cross-model review of the current review scope (branch diff plus staged, unstaged, untracked changes) from the opposite vendor's model. Catches spec drift, missing edge cases, and fake tests self-review cannot see. Use before merging, after a tricky change, or a debug second opinion.

repo-harness-product

Canonical rule owner for PRD drafting, Sprint planning/execution, and native Goal-session preparation from repo-harness planning artifacts.

repo-harness-setup

Canonical rule owner for installing, migrating, upgrading, repairing, scaffolding, and capability-configuring the repo-harness workflow in a repository.

repo-harness-chatgpt-bridge

Use when setting up or operating the repo-harness ChatGPT MCP Connector, bridging ChatGPT planning artifacts into Codex execution through repo-harness PRDs, sprints, checks, and handoffs.

repo-harness-chatgpt-browser

Use when the user wants Codex to consult their logged-in ChatGPT Web session through repo-harness browser engine for planning, architecture review, PRD critique, or Codex goal generation.

claude-plan

Get an independent architecture/implementation plan from Anthropic Claude (Fable, a different vendor's model) running Claude Code's native plan mode, from inside a non-Claude host such as Codex. Use mid-execution when work hits a genuine design fork or high-stakes decision that should not be settled unilaterally. Not for routine planning — that stays in the host's own plan tooling. Explicit invocation only. Triggers: "claude plan", "ask fable for a plan", "fable planning", "问 fable", "让 fable 出方案", "外脑出方案".

claude-review

Get an independent cross-model code review from Anthropic Claude (a different vendor's model) on the current review scope: branch diff plus staged, unstaged, and untracked working tree changes, from inside a non-Claude host such as Codex. A different training distribution has non-overlapping blind spots, so Claude catches spec ambiguity, missing edge cases, and fake tests that Codex's self-review cannot see. Use before merging, after a tricky change, or for a debug second opinion. Triggers: "claude review", "second opinion", "ask claude", "outside voice", "让 claude 审", "找外部意见", "二审".