Skills

harness-engineering

harness-engineering is a skill in github/awesome-copilot, last changed 15 Jun 2026. It can name web addresses. Our pattern check flagged nothing at commit 920e3b9 on 26 Oct 2026.

Pattern check: nothing flagged · commit 920e3b9 · 26 Oct 2026

Install
From the author
Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.
Licence
MIT
Repo stars
40.5k
Folder last changed
15 Jun 2026 (opens in a new tab)
Publisher
github
Files
1 file
Checked
920e3b9 (opens in a new tab) · 26 Oct 2026

Install

Each tab says whether it installs commit 920e3b9, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 920e3b9, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/github/awesome-copilot.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 920e3b927a553642834af13097f53f6f716947db &&
  git -C "$tmp" sparse-checkout set -- skills/harness-engineering &&
  git -C "$tmp" checkout -q 920e3b927a553642834af13097f53f6f716947db &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/harness-engineering &&
  cp -R "$tmp"/skills/harness-engineering/. .claude/skills/harness-engineering/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 920e3b9. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

Pattern check

Pattern check: nothing flagged · commit 920e3b9 · 26 Oct 2026

We checked every text file in this skill, at commit 920e3b9 on 26 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://github.com/baskduf/harness-starter-kit

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses
  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      The description is 279 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

1 file

PathSize
SKILL.md (opens in a new tab)7.7 KB

More from github/awesome-copilot

  • acquire-codebase-knowledge

    github/awesome-copilot

    Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +1

    MIT · 40.5k repo stars · Updated 15 Sept 2026

  • acreadiness-assess

    github/awesome-copilot

    Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.

    Pattern check: Nothing flaggedWhat it can touch: Downloads software · Runs shell commands +2

    MIT · 40.5k repo stars · Updated 3 May 2026

  • acreadiness-generate-instructions

    github/awesome-copilot

    Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.

    Pattern check: Nothing flaggedWhat it can touch: Downloads software · Runs shell commands +1

    MIT · 40.5k repo stars · Updated 3 May 2026

  • acreadiness-policy

    github/awesome-copilot

    Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.

    Pattern check: Nothing flaggedWhat it can touch: Downloads software · Runs shell commands +1

    MIT · 40.5k repo stars · Updated 3 May 2026

  • ad-campaign-analyzer

    github/awesome-copilot

    Use this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like "analyze my ad campaigns", "where am I wasting ad spend", "reallocate my ad budget", "which ads are actually working", or "ROAS analysis". Do not trigger for campaign planning or creative generation without performance data.

    Pattern check: Nothing flaggedWhat it can touch: Names web addresses

    MIT · 40.5k repo stars · Updated 23 Jul 2026

  • add-educational-comments

    github/awesome-copilot

    Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.

    Pattern check: Nothing flaggedWhat it can touch: Names web addresses

    MIT · 40.5k repo stars · Updated 23 Feb 2026

All skills in github/awesome-copilot