New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Repo Harness Cross Review

by Ancienttwo in Ancienttwo/repo-harness

Independent acceptance review through the persistent fleet deep-reasoner task-agent in Herdr.

MITAuto-check passed

Install Repo Harness Cross Review

skills CLI
$ npx skills add Ancienttwo/repo-harness --skill repo-harness-cross-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ancienttwo/repo-harness repo-harness-cross-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ancienttwo/repo-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills/repo-harness-cross-review .claude/skills/repo-harness-cross-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
repo-harness-cross-review
GitHub stars
434
Token cost
~394 tokens
SKILL.md length
143 words
Files
3 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Independent acceptance review through the persistent fleet deep-reasoner task-agent in Herdr.

  • SKILL.md covers Mode Selection and Boundaries
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Repo Harness Cross Review is an agent skill from Ancienttwo/repo-harness. Independent acceptance review through the persistent fleet deep-reasoner task-agent in Herdr. Generic review owns scope, request-bound Result validation and typed Receipt; the old direct advisory runtime is retired.

Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/codex-mode.md` and `references/generic-review.md`).

The repository describes itself as: File-backed workflow harness for reliable Claude Code and Codex sessions. The licence is MIT.

Example prompts

  • “/repo-harness-cross-review”

What it can do on your machine

Read from SKILL.md and the folder at commit 461e054. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Repo Harness Cross Review loads about 394 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 143 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~394
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ancienttwo/repo-harness at commit 461e054, republished under its MIT licence (© Ancienttwo). 143 words, ~394 tokens.

Download SKILL.mdSave it as .claude/skills/repo-harness-cross-review/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
repo-harness-cross-review
description
Independent acceptance review through the persistent fleet deep-reasoner task-agent in Herdr. Generic review owns scope, request-bound Result validation and typed Receipt; the old direct advisory runtime is retired.
when_to_use
cross review, second opinion, outside voice, codex review, independent review, 让 codex 审, 找外部意见, 二审

repo-harness-cross-review

Bot entrypoint. Canonical routing guidance for the existing generic review domain. Runtime ownership lives in src/effects/review/generic-review.ts, the OAR host and src/effects/terminal/task-session.ts; the Skill does not implement a provider.

Mode Selection

  • Acceptance through persistent Herdr task-agent: references/generic-review.md.
  • Migration from the retired direct Codex advisory command: references/codex-mode.md.
  • Explicit harness selection belongs to repo-harness review round --harness.

Boundaries

Prepare verification and the contract before review. The existing fleet deep-reasoner role, addressed Herdr pane, isolated reviewer checkout and OAR Session own the run. History/idle are observations; the request-bound file Result and generic-review Receipt own acceptance. Unknown model, delivery or cleanup stays unverified or pending. Never synthesize PASS, alias the retired command, replay an ambiguous request or bypass a frozen reviewer policy. Review does not merge; the owner makes that separate decision. Use only the documented admitted runtime/isolation boundary; library permission approval is not an OS sandbox.

© Ancienttwo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in assets/skills/repo-harness-cross-review of Ancienttwo/repo-harness.

  • SKILL.md
  • references/codex-mode.md
  • references/generic-review.md

Open the folder on GitHubat commit 461e054

Compare with similar skills

Repo Harness Cross Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Repo Harness Cross Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Repo Harness Cross Review this skillAncienttwo/repo-harness434—~394Automated safety check: PassMIT
Deepseek Reasonruvnet/ruflo74k—~626Automated safety check: NotesMIT
QA Acceptancepaperclipai/paperclip100k—~964Automated safety check: PassMIT
Swift Actor Persistenceaffaan-m/ECC277k4 repos~1.2kAutomated safety check: PassMIT
Session Persistruvnet/ruflo74k—~415Automated safety check: NotesMIT
Iot Fleetruvnet/ruflo74k—~210Automated safety check: PassMIT

Similar skills

  • Deepseek Reason

    ruvnet/ruflo

    Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.

    74k GitHub stars~626 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

  • QA Acceptance

    paperclipai/paperclip

    Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.

    100k GitHub stars~964 tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Swift Actor Persistence

    affaan-m/ECC

    Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

    277k GitHub starsUsed in 4 repos~1.2k tokens
    MobileAuto-check passed

  • Session Persist

    ruvnet/ruflo

    Persist and restore agent sessions across conversations with state snapshots

    74k GitHub stars~415 tokensUpdated yesterday
    Auto-check: notes

  • Iot Fleet

    ruvnet/ruflo

    Create and manage Cognitum Seed device fleets with firmware policies

    74k GitHub stars~210 tokensUpdated yesterday
    Auto-check passed

  • Fleet

    asheshgoplani/agent-deck

    Fan out a fleet of independent agent-deck child sessions from inside a session and check their progress non-blockingly.

    1.1k GitHub stars~4.2k tokensUpdated yesterday
    Auto-check passed

More from Ancienttwo/repo-harness

All 13 skills in this repo

  • Windows Python First

    Ancienttwo/repo-harness

    A skill your agent uses for agent tasks in native Windows that need file edits, text conversion, JSON processing, or shell commands with quoting or encoding problems.

    435 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Repo Harness

    Ancienttwo/repo-harness

    Route explicit repo-harness commands and active harness work.

    435 GitHub stars~498 tokensUpdated today
    Auto-check passed

  • Development Scheduler

    Ancienttwo/repo-harness

    在 repo-harness session 或 Bot 中通过 Herdr 调度开发任务、跟进阻碍、组织独立审查和安全交接；用于多角色开发协调，不用于单次代码修改或只读状态查询。

    435 GitHub stars~703 tokensUpdated today
    Auto-check passed

  • Repo Harness Chatgpt

    Ancienttwo/repo-harness

    Canonical rule owner for repo-harness ChatGPT integration -- Oracle-first browser/GPT Pro consult and continuation, advisory orchestration, MCP Connector setup, MCP bridge planning handoff, and…

    435 GitHub stars~587 tokensUpdated today
    Auto-check passed

  • Repo Harness Setup

    Ancienttwo/repo-harness

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

    435 GitHub stars~474 tokensUpdated today
    Auto-check passed

  • Repo Harness Ship

    Ancienttwo/repo-harness

    Close out verified harness work only when the user explicitly asks to commit, push, open a PR, merge, or clean merged worktrees.

    435 GitHub stars~251 tokensUpdated today
    Auto-check passed

Questions about Repo Harness Cross Review

What does Repo Harness Cross Review do?

Independent acceptance review through the persistent fleet deep-reasoner task-agent in Herdr. Repo Harness Cross Review is an agent skill from Ancienttwo/repo-harness. Independent acceptance review through the persistent fleet deep-reasoner task-agent in Herdr.

How do I install Repo Harness Cross Review in Claude Code?

Run `npx skills add Ancienttwo/repo-harness --skill repo-harness-cross-review -a claude-code`. Or copy the skill folder (assets/skills/repo-harness-cross-review in Ancienttwo/repo-harness) into .claude/skills/repo-harness-cross-review in your project. Claude Code loads it when a task matches its description.

How do I install Repo Harness Cross Review in Codex?

Run `npx skills add Ancienttwo/repo-harness --skill repo-harness-cross-review -a codex`. Or copy the skill folder (assets/skills/repo-harness-cross-review in Ancienttwo/repo-harness) into .agents/skills/repo-harness-cross-review in your project. Codex loads it when a task matches its description.

Can I use Repo Harness Cross Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ancienttwo/repo-harness --skill repo-harness-cross-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/repo-harness-cross-review, .gemini/skills/repo-harness-cross-review, .github/skills/repo-harness-cross-review and .opencode/skills/repo-harness-cross-review in your project.

What does Repo Harness Cross Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Repo Harness Cross Review is instructions for the agent only.

Does Repo Harness Cross Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Repo Harness Cross Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Repo Harness Cross Review use?

Repo Harness Cross Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Repo Harness Cross Review use?

About 394 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Repo Harness Cross Review?

Skills that share tags, products or a category with Repo Harness Cross Review: Deepseek Reason (ruvnet/ruflo, 74k stars), QA Acceptance (paperclipai/paperclip, 100k stars), Swift Actor Persistence (affaan-m/ECC, 277k stars) and Session Persist (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Repo Harness Cross Review?

Ancienttwo (a GitHub user) maintains it in Ancienttwo/repo-harness, which has 434 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.

Source: Ancienttwo/repo-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.