repo-harness-cross-review

repo-harness-cross-review is a skill for Claude Code from Ancienttwo/repo-harness. It costs 67 tokens per session (480 once invoked), scanned A, original, MIT.

A review helper that asks an independent coding agent to inspect your branch diff and all staged, unstaged, and untracked changes.

In plain words
What is it for?
Use it before merging an important change, after writing a specification or tests, or during difficult debugging. It reports findings as pass or fail based on their priority.
Why use it?
It provides a second opinion before a merge or when a bug is hard to diagnose. It helps expose serious problems, unclear requirements, and weak tests that the original author may miss.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it before merging an important change, after writing a specification or tests, or during difficult debugging. It reports findings as pass or fail based on their priority.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ancienttwo/repo-harness/repo-harness-cross-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ancienttwo/repo-harness --skill repo-harness-cross-review
Clone the repo
git clone --depth 1 https://github.com/Ancienttwo/repo-harness

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for repo-harness-cross-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-cross-review/github.svg)](https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-cross-review)
Your own site
<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-cross-review"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-cross-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for repo-harness-cross-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-cross-review"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-cross-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00480
Opus 5 $0.00034 $0.00240
Sonnet 5 $0.00013 $0.00096
Haiku 4.5 $0.00007 $0.00048

Measured 5d ago against content hash 0ebbef2c857a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repo-harness-cross-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

assets/skills/repo-harness-cross-review/SKILL.md · 39 lines

What it actually says

repo-harness-cross-review

Canonical rule owner for independent outside review. Scope capture, provider invocation, timeout, structured-output validation, 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 -> direct Codex: references/codex-mode.md.
  • Inside Codex -> official codex@openai-codex plugin app-server: references/codex-plugin-mode.md.
  • Explicit Claude acceptance review -> references/claude-mode.md.
  • An explicit provider request 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: direct Codex and the plugin app-server both use a read-only sandbox.
  • Bounded: 2 provider attempts, then SKIPPED -- advisory, non-blocking (exit 0). Do not re-run it or narrow the diff to retry. degraded_scope and stale_scope block (exit 1). Never a synthesized pass.
  • Never produces or verifies a merge-gate receipt; that judge is separate.
Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago Changed · -3 lines 0ebbef2c857a
  2. 6d ago Changed · +4 lines fe6d6d4daec1
  3. 12d ago First seen · 38 lines · 67 tokens per session scan A 9c5c66ead2ba

Subscribe to this mod's changes

repo-harness-cross-review is a skill published in the GitHub repository Ancienttwo/repo-harness (431 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 480 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

openlore-execute-refactor

Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.

clay-good/OpenLore · 41 tokens

openlore-review-changes

Review code changes using OpenLore risk, call, coverage, and cluster evidence without editing code. Use when asked for a change review, pre-PR safety check, or merge recommendation.

clay-good/OpenLore · 44 tokens

openclaw-github-dedupe

Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.

vincentkoc/dotskills · 68 tokens

openclaw-pr-batch-sweep

Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…

vincentkoc/dotskills · 95 tokens

semantic-slicing

Build local semantic review slices by combining clawpatch feature maps, deepsec threat candidates, visual review maps, and optional gitcrawl/discrawl evidence for repos such as openclaw/openclaw.

vincentkoc/dotskills · 43 tokens

technical-deslop

Remove AI-style noise from staged and branch diffs while preserving behavior and repository style.

vincentkoc/dotskills · 21 tokens