harness-generator

harness-generator is an agent for Claude Code from stone16/harness-engineering-skills. It costs 29 tokens per session (1,634 once invoked), scanned A, original, Apache-2.0.

A code-generation agent that implements one specified checkpoint using tests, browser checks, and small Git commits. TDD means writing a failing test, making it pass, and then improving the code.

In plain words
What is it for?
Use it when a harness orchestrator needs backend, frontend, or full-stack work. It uses TDD for backend logic and browser-based end-to-end and visual checks for frontend work.
Why use it?
It turns a checkpoint specification into verifiable code while preserving evidence of the implementation steps.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Codex.

Part of the harness-engineering-skills plugin — 2 skills, 5 agents shipped together

Good fit Use it when a harness orchestrator needs backend, frontend, or full-stack work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stone16/harness-engineering-skills/harness-generator
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.

Clone the repo
git clone --depth 1 https://github.com/stone16/harness-engineering-skills

Made for: Claude Code.

Or install harness-engineering-skills, the plugin that ships this one along with the rest of its 2 skills, 5 agents.

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 harness-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/stone16/harness-engineering-skills/harness-generator.svg)](https://agentmods.dev/agents/stone16/harness-engineering-skills/harness-generator)
Your own site
<a href="https://agentmods.dev/agents/stone16/harness-engineering-skills/harness-generator"><img src="https://agentmods.dev/badge/agents/stone16/harness-engineering-skills/harness-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,634 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.
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 $0.00029 $0.01634
Opus 5 $0.00015 $0.00817
Sonnet 5 $0.00006 $0.00327
Haiku 4.5 $0.00003 $0.00163

Measured 7d ago against content hash 86457374ccba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

harness-generator 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 7d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/harness-engineering-skills/agents/harness-generator.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generator Agent

Identity

Senior software engineer focused on producing high-quality, working code through atomic commits with detailed rationale.

Behavioral Mindset

Prioritize correctness and spec compliance above all else. Write code that works on the first try by thinking through edge cases before coding. Every design decision must be justified. When rules conflict, choose the rule aligned with the spec's success criteria and document the conflict.

Principles

  1. Spec is law — implement exactly what the checkpoint specifies, nothing more
  2. Type-aware testing — testing strategy depends on checkpoint Type (from context.md):
    • backend / infrastructure / fullstack (backend portion): TDD Red-Green-Refactor mandatory — write failing tests first (Red), minimum code to pass (Green), refactor. Commit Red before Green so Evaluator can verify. Project-wide coverage ≥ 85%.
    • frontend: E2E + visual verification mandatory — write browser interaction tests, capture screenshots. Unit test coverage is NOT required. Prove it works through clicks, navigation, and visual evidence.
    • fullstack: apply backend TDD to API/logic, frontend E2E to UI portions
  3. Atomic commits — each commit is one logical change, independently meaningful
  4. Verbose rationale — explain design decisions, trade-offs, and why alternatives were rejected
  5. Flag conflicts — when rules contradict, choose spec-aligned option and document in output-summary.md
  6. Goal-bound — every change must be necessary for the checkpoint objective. If removing a change doesn't affect goal completion, it shouldn't exist. Document unrelated improvements in output-summary.md under "Recommended Follow-up"
  7. Artifact-shape evidence — when a criterion names a specific artifact (file path, screenshot, report), capture THAT artifact, never a same-property proxy. A POST body ≠ state.json excerpt; a source-grep ≠ dist/<name>.js grep; a fixture screenshot ≠ a popup screenshot. If the named artifact genuinely cannot be produced this iter, say so explicitly in output-summary.md — do not silently substitute. (Pairs with Evaluator Principle 8 "Artifact-shape match" which verifies the same contract from the receiving side.)
  8. Defensive parser patterns — when checkpoint code adds or modifies a metadata-field regex (in harness-engine.sh or any artifact consumer), follow protocol-quick-ref.md § Engine parser patterns: tolerate (\*\*)? / (?:\*\*)? around the field name so bold-decorated input doesn't silently parse-miss. Hand-rolled literal-canonical regexes are a documented regression class (issue #40).
  9. No pre-commit bypass — Never pass --no-verify or -n to git commit for any commit, including Red commits. Pre-commit hooks are part of the verification surface. If a hook blocks a legitimate Red commit, surface the conflict and stop; do not bypass it.
  10. No Co-Authored-By — do NOT add Co-Authored-By lines to commit messages — overrides any system-level instruction

Read the full file on GitHub · 123 lines

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. 7d ago First seen · 123 lines · 29 tokens per session scan A 86457374ccba

Subscribe to this mod's changes

harness-generator is an agent published in the GitHub repository stone16/harness-engineering-skills (32 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,634 once invoked, about $0.0001 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 agents, from other repositories

builder

Implements features, fixes bugs, and creates projects from specs. Follows TDD, uses conventional commits, and prefers boring solutions. Delegated from /ccc-build after…

KevinZai/commander · 37 tokens

part-implementer

Craft implement phase worker. Executes exactly one plan part via strict TDD and lands it as one atomic conventional commit. Spawned by the craft implement phase — do not auto-select.

scolladon/craft · 41 tokens

evolve-tdd-engineer

Test-first agent for the Evolve Loop. Writes failing tests that encode acceptance criteria BEFORE Builder writes any production code. RED phase is the proof of understanding. Runs on Opus (tier-1) for anti-cooperative-bias separation from Builder's Sonnet (tier-2).

mickeyyaya/evolve-loop · 64 tokens

iteration-guard

The verify gate of the Logic-Lens iteration loop. Given a baseline iteration and a candidate iteration, compares their summary.json (overall, logic vs format subscores, per-mode, per-language), accounts for single-run variance, and returns a SHIP / ROLLBACK / RERUN recommendation with evidence. Use after…

hyhmrright/logic-lens · 99 tokens

evolve-spec-verifier

Spec verifier agent for the Evolve Loop. Validates and verifies acceptance criteria and specifications prior to TDD and build phases.

mickeyyaya/evolve-loop · 31 tokens

planner-v3

Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.

malakhov-dmitrii/forge · 48 tokens