/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
$ npx -y skills add Ancienttwo/repo-harness --skill repo-harness-cross-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/repo-harness-cross-review
Context preview
The summary Claude sees to decide when to auto-load this skill.
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
SKILL.md
repo-harness-cross-review.SKILL.mdname: repo-harness-cross-review
description: 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.
when_to_use: "cross review, second opinion, outside voice, claude review, codex review, 让 claude 审, 让 codex 审, 找外部意见, 二审"
repo-harness-cross-review
Canonical rule owner for opposite-provider review. Scope capture, provider invocation, timeout, transcript recovery, and error classification live in code (`src/core/review`, `src/effects/review`, `src/cli/commands/cross-review.ts`); this package owns only when to invoke, how to interpret findings, and the boundaries below.
Mode Selection
- Inside Claude Code -> Codex's outside opinion: `references/codex-mode.md`.
- Inside Codex -> Claude's outside opinion: `references/claude-mode.md`.
- An explicit provider name request always wins over the host default.
When to use
- Before merging an important diff (last gate).
- After writing a spec/tests -- find ambiguity and weak assertions.
- A hard bug whose root cause is unclear (independent diagnosis).
Interpreting findings
- Present the transcript verbatim -- never summarize or soften it.
- Any `[P1]` finding -> **FAIL** (do not merge until addressed). Only `[P2]` or none -> **PASS**.
- Agreement raises confidence; divergence is where to dig. A recommendation, not a decision -- you decide.
Boundaries
- Read-only: the provider never edits code (no Bash/Edit/Write for Claude; read-only sandbox for Codex).
- A provider failure (timeout, empty output, malformed transcript, auth failure, nonzero exit, degraded scope) is explicit. Never a fallback, never a synthesized pass.
- Never produces or verifies a `merge-gate` receipt; that judge is separate.
Read more
name: repo-harness-cross-review description: 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. when_to_use: "cross review, second opinion, outside voice, claude review, codex review, 让 claude 审, 让 codex 审, 找外部意见, 二审"
repo-harness-cross-review
Canonical rule owner for opposite-provider review. Scope capture, provider invocation, timeout, transcript recovery, and error classification live in code (`src/core/review`, `src/effects/review`, `src/cli/commands/cross-review.ts`); this package owns only when to invoke, how to interpret findings, and the boundaries below.
Mode Selection
- Inside Claude Code -> Codex's outside opinion: `references/codex-mode.md`.
- Inside Codex -> Claude's outside opinion: `references/claude-mode.md`.
- An explicit provider name request always wins over the host default.
When to use
- Before merging an important diff (last gate).
- After writing a spec/tests -- find ambiguity and weak assertions.
- A hard bug whose root cause is unclear (independent diagnosis).
Interpreting findings
- Present the transcript verbatim -- never summarize or soften it.
- Any `[P1]` finding -> **FAIL** (do not merge until addressed). Only `[P2]` or none -> **PASS**.
- Agreement raises confidence; divergence is where to dig. A recommendation, not a decision -- you decide.
Boundaries
- Read-only: the provider never edits code (no Bash/Edit/Write for Claude; read-only sandbox for Codex).
- A provider failure (timeout, empty output, malformed transcript, auth failure, nonzero exit, degraded scope) is explicit. Never a fallback, never a synthesized pass.
- Never produces or verifies a `merge-gate` receipt; that judge is separate.
File-backed workflow harness for reliable Claude Code and Codex sessions.
Repo: Ancienttwo/repo-harness
Other skills on repo-harness.
- /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
Open skill - /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.
Open skill - /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.
Open skill - /repo-harness-product
Canonical rule owner for PRD drafting, Sprint planning/execution, and native Goal-session preparation from repo-harness planning artifacts.
Open skill - /repo-harness-setup
Canonical rule owner for installing, migrating, upgrading, repairing, scaffolding, and capability-configuring the repo-harness workflow in a repository.
Open skill

