English | 한국어 | 日本語 | 简体中文 | 繁體中文

Harness Starter Kit

A prompt-first starter kit for turning repeated coding-agent mistakes into durable repository instructions, checks, memory, and evaluation.

Product Effects

Harness Starter Kit does not position repository harnessing as raw coding performance tuning. Its product effect is operational: make agent work safer to run, easier to diagnose, and easier to improve from repository evidence.

• Isolate agent work safely. Run agent tasks inside clear repository boundaries so hidden or sensitive files, generated outputs, credentials, and forbidden paths stay out of normal task flow.
• Turn failures into diagnosis. Separate functional, schema, workflow, boundary, timeout, and hidden-access failures instead of reducing an agent result to one pass/fail label.
• Transfer repository conventions. Preserve local API style, documentation placement, validation commands, and review expectations in durable repo guidance that agents can follow repeatedly.
• Create an improvement loop. Convert observed mistakes into instructions, checks, failure records, decision memory, benchmark tasks, or review points so the next agent run has better operating context.

Quick Start

Open the target repository with your coding agent and give it this prompt.

Use this kit to apply harness engineering to this repository:

https://github.com/harnessworks/harness-starter-kit

Clone the kit into ./harness-starter-kit if it is not already present, read it,
then apply its prompt-first harness engineering workflow to this repository.

Requirements:
- Treat the current working directory as the target repository.
- Treat ./harness-starter-kit as read-only reference material after cloning.
- Inspect this repository before editing.
- Preserve existing architecture, tools, package manager, commands, docs, and
  conventions.
- Do not blindly copy templates.
- Add only the minimum useful harness pieces.
- Prefer updating existing docs/configs over duplicating them.
- Do not overwrite or delete existing files without explaining why.
- If I ask for /harness doctor, use
  ./harness-starter-kit/commands/harness-doctor.md.
- If I ask for /harness update after adoption, use
  ./harness-starter-kit/commands/harness-update.md to refresh the kit reference,
  record .harness/source.json, and selectively update target harness files
  without blindly overwriting existing files.
- If I ask for /harness refresh after adoption, use
  ./harness-starter-kit/commands/harness-refresh.md to review existing harness
  docs, rules, knowledge records, and checks for stale or duplicated guidance.
  Do not delete, archive, move, or rename files without my explicit approval for
  the specific files.
- If I ask for /harness review sub-agent, use
  ./harness-starter-kit/commands/harness-review.md and treat the request as
  explicit permission to use a read-only reviewer subagent when available and
  permitted by the active runtime and tool instructions. If unavailable,
  blocked, not permitted, or failed, report the fallback reason.
- If I ask for /harness review, use
  ./harness-starter-kit/commands/harness-review.md to review the current change
  set from an opposing harness-engineering perspective. Report findings,
  missing checks, overreach, durable memory gaps, and follow-up recommendations
  without modifying files unless I explicitly ask you to apply fixes after the
  review.

Expected result:
- project-specific AGENTS.md or updated existing agent instructions
- knowledge store if no equivalent exists
- lightweight drift checks based on this repo's real rules
- local verification commands using existing tools
- adoption report with files changed, checks to run, assumptions, remaining
  manual steps, failure memory, effectiveness measurement plan,
  normal/focused/manual gate placement, and whether
  ./harness-starter-kit should be removed, ignored, or kept before commit

For the full prompt and workflow details, see docs/prompts/apply-to-target-repo.md and docs/adoption-workflow.md.

💫 If this kit helps you, a GitHub star would be appreciated. 💫

Harness Theory

Harness engineering treats the repository as the durable operating environment for coding agents:

Harness = Instructions + Constraints + Feedback + Memory + Evaluation + Governance

Harness health is different from agent effectiveness. Harness Doctor can scan for durable repository evidence, but it cannot prove that agents make fewer mistakes. Measure that separately with task outcomes and effectiveness reports. See docs/theory/harness-engineering.md for the model.

Every recurring agent failure should be converted into at least one durable artifact: a clearer instruction, an automated constraint, a test or CI check, a decision or failure record, or a drift check.

Command Flow

The /harness ... names below are prompt conventions by default, not built-in editor commands. Type or paste them into your coding agent chat. In editors such as Cursor, they will not appear in the command palette unless you separately add matching custom slash commands.

Think about the commands by user stage:

Quick rule:

• Use doctor to inspect.
• Use adopt to start.
• Use review before finishing work.
• Use update when the kit version changes.
• Use refresh when this repo's existing harness guidance gets stale.

See commands/ for full workflows: adopt, doctor, update, refresh, and review.

Install Agent Skills

Harness workflows are prompt-first by default, but the same workflows are also published as runtime-native skills for Codex and Claude Code.

Codex

codex plugin marketplace add harnessworks/harness-agent-skills-marketplace --ref v0.1.16

Restart Codex, open the Plugins screen, select Harnessworks, and install harness-agent-skills.

Use the same command model in every runtime:

Start:      $harness doctor → $harness adopt
Daily:      $harness review
Maintain:   $harness update or $harness refresh

Common commands:

$harness doctor
$harness adopt
$harness review

Maintenance commands:

$harness update
$harness refresh

Claude Code

claude plugin marketplace add harnessworks/harness-agent-skills-marketplace@v0.1.16
claude plugin install harness-agent-skills@harnessworks

Use the router command:

Start:      /harness-agent-skills:harness doctor → /harness-agent-skills:harness adopt
Daily:      /harness-agent-skills:harness review
Maintain:   /harness-agent-skills:harness update or /harness-agent-skills:harness refresh

Common commands:

/harness-agent-skills:harness doctor
/harness-agent-skills:harness adopt
/harness-agent-skills:harness review

Maintenance commands:

/harness-agent-skills:harness update
/harness-agent-skills:harness refresh

The source package lives in agent-skills/. For direct repo-local installs, packaging details, and update behavior, see docs/agent-skills-package.md.

How Adoption Works

python harness-starter-kit/scripts/apply_harness.py --target . --profile generic --dry-run

Contributors

Thanks to everyone who has helped shape this kit through code, docs, reviews, examples, translations, and dogfooding.

Recognition

Listed in:

• Awesome-AI-Agents as an AI agent tooling project.
• github/awesome-copilot as a Copilot customization resource.

License

This project is licensed under the MIT License.