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

by Ancienttwo in Ancienttwo/repo-harness

Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill.

MITAuto-check passedTesting & QA

Install Repo Harness

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

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

GitHub CLI
$ gh skill install Ancienttwo/repo-harness repo-harness --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/evals/frontier-stress-test/treatment .claude/skills/repo-harness && 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
GitHub stars
434
Token cost
~533 tokens
SKILL.md length
261 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill.

  • Works in 7 steps: Resolve environment facts from CASE.md;… → Model only high-impact decisions and… → Emit at most three frontier questions… → …
  • Tasks that involve Load testing
  • SKILL.md covers Eligibility, Protocol and Hard kills
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Repo Harness is an agent skill from Ancienttwo/repo-harness. Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill.

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Load testing. The repository describes itself as: File-backed workflow harness for reliable Claude Code and Codex sessions. The licence is MIT.

When your agent uses it

  • Tasks that involve Load testing

Example prompts

  • “/repo-harness”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Resolve environment facts from CASE.md; do not ask the user for known facts.
  2. Model only high-impact decisions and their prerequisites. A decision enters
  3. Emit at most three frontier questions per round. Each question includes a
  4. Stop after two rounds per invocation. Further expansion requires explicit
  5. Never answer a user-owned decision. Mark it [UNKNOWN:BLOCKING] and keep the
  6. Persist resolved decisions into existing authority: canonical terms to
  7. Shared understanding requires user confirmation. Never mark an unresolved

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 loads about 533 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~533

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). 261 words, ~533 tokens.

Download SKILL.mdSave it as .claude/skills/repo-harness/SKILL.md (or your agent's skills folder).
name
repo-harness
description
Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill.

Bounded frontier stress test — eval treatment

This is an evaluation-only delta over the fixture's minimum-effective-interview baseline. It has no authority to approve or implement a plan.

Eligibility

Use the treatment only when explicitly requested or when a case changes high-risk architecture, data authority or ownership, security, permissions, money, deletion, concurrency, recovery semantics, or a hard-to-reverse public interface. Bypass it for small bug fixes, decision-complete acceptance criteria, documentation, formatting, and renames.

Protocol

  1. Resolve environment facts from CASE.md; do not ask the user for known facts.
  2. Model only high-impact decisions and their prerequisites. A decision enters the current frontier only after every prerequisite is resolved.
  3. Emit at most three frontier questions per round. Each question includes a recommended default and the effect of every option.
  4. Stop after two rounds per invocation. Further expansion requires explicit continue; unvisited branches remain explicit.
  5. Never answer a user-owned decision. Mark it [UNKNOWN:BLOCKING] and keep the plan Draft.
  6. Persist resolved decisions into existing authority: canonical terms to docs/spec.md#Canonical Terms; user need/non-goal to PRD; boundary and trade-off to Plan; allowed scope and failure semantics to Plan + Contract; verifiable behavior to Contract exit_criteria; long-lived architecture to its architecture module/request. Reversible defaults use [ASSUMED].
  7. Shared understanding requires user confirmation. Never mark an unresolved plan Approved and never start implementation from this mode.

Hard kills

  • Never create a parallel context, ADR, decision-tree, or grill-session artifact.
  • Never expose the transient decision graph as durable authority.
  • Never ask a downstream question in the same round as its unresolved prerequisite.
  • Never trigger on a simple or decision-complete task.

© 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

Just SKILL.md in evals/frontier-stress-test/treatment of Ancienttwo/repo-harness.

Open the folder on GitHubat commit 461e054

Compare with similar skills

Repo Harness 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Repo Harness this skillAncienttwo/repo-harness434—~533Automated safety check: PassMIT
Writing Livekit Scenarioslivekit-examples/agent-starter-python2641 repos~2.5kAutomated safety check: PassMIT
Go Testingcxuu/golang-skills1731 repos~1.3kAutomated safety check: PassApache-2.0
Goalcraftgrp06/goalcraft102—~3.8kAutomated safety check: PassMIT
Thinking Partnermattnowdev/thinking-partner206—~4.4kAutomated safety check: PassMIT
Visionkunchenguid/vision331—~2.9kAutomated safety check: PassMIT

Similar skills

  • Writing Livekit Scenarios

    livekit-examples/agent-starter-python

    Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them.

    264 GitHub starsUsed in 1 repo~2.5k tokens
    Testing & QAAuto-check passed

  • Go Testing

    cxuu/golang-skills

    A skill your agent uses when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff.

    173 GitHub starsUsed in 1 repo~1.3k tokens
    Testing & QAAuto-check passed

  • Goalcraft

    grp06/goalcraft

    Turn a rough draft, vague ambition, or messy task brief into a powerful Codex /goal objective for persistent, evidence-checked work.

    102 GitHub stars~3.8k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed

  • Thinking Partner

    mattnowdev/thinking-partner

    A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly.

    206 GitHub stars~4.4k tokensUpdated 6 mo ago
    Testing & QAAuto-check passed

  • Vision

    kunchenguid/vision

    Draft and stress-test a VISION.md for a repository, then iterate with the author on an interactive review board until approved.

    331 GitHub stars~2.9k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Volt Load Testing

    owenHochwald/volt

    Safely exercise and evaluate HTTP APIs with the Volt CLI, including authenticated requests, JSON bodies, staged load, machine-readable results, performance baselines, and before/after comparisons.

    141 GitHub stars~1.2k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed

More from Ancienttwo/repo-harness

All 12 skills in this repo

  • 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。

    434 GitHub stars~703 tokensUpdated today
    Auto-check passed

  • Repo Harness

    Ancienttwo/repo-harness

    Route explicit repo-harness commands and active harness work.

    434 GitHub stars~365 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…

    434 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.

    434 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.

    434 GitHub stars~251 tokensUpdated today
    Auto-check passed

  • Repo Harness Check

    Ancienttwo/repo-harness

    Plan scoped harness work, review a plan, or assess recorded checks and risk.

    434 GitHub stars~354 tokensUpdated today
    Auto-check passed

Categories

Questions about Repo Harness

What does Repo Harness do?

Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill. Repo Harness is an agent skill from Ancienttwo/repo-harness. Eval-only bounded frontier stress test for complex repo-harness planning; never installed as a managed Skill.

When should I use Repo Harness?

Repo Harness fits situations like: tasks that involve Load testing.

How do I install Repo Harness in Claude Code?

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

How do I install Repo Harness in Codex?

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

Can I use Repo Harness 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 -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, .gemini/skills/repo-harness, .github/skills/repo-harness and .opencode/skills/repo-harness in your project.

What does Repo Harness need to run?

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

Does Repo Harness 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 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 use?

Repo Harness 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 use?

About 533 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Repo Harness?

Skills that share tags, products or a category with Repo Harness: Writing Livekit Scenarios (livekit-examples/agent-starter-python, 264 stars), Go Testing (cxuu/golang-skills, 173 stars), Goalcraft (grp06/goalcraft, 102 stars) and Thinking Partner (mattnowdev/thinking-partner, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Repo Harness?

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.