harness-create

harness-create is a skill for Claude Code, Codex from nnabuuu/harness-engineering-toolkit. It costs 145 tokens per session (2,479 once invoked), scanned A, original, MIT.

A tool for turning a goal into a running overnight harness: a repeatable project that directs an AI agent through work and checks the results. It can start with an interview or an existing `HARNESSSPEC.md` specification, and supports document, code, and investigation projects.

In plain words
What is it for?
Use it to plan a harness, create its specification, generate the project, resume interrupted work, limit cost, inspect status, and register or remove it from DAGU, a workflow scheduler.
Why use it?
It turns an unclear objective into written requirements, repeatable steps, progress tracking, and evaluation files, making long unattended runs easier to control.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nnabuuu/harness-engineering-toolkit/harness-create
Any agent
npx skills add nnabuuu/harness-engineering-toolkit --skill harness-create
Clone the repo
git clone --depth 1 https://github.com/nnabuuu/harness-engineering-toolkit

Made for: Claude Code, Codex.

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-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/nnabuuu/harness-engineering-toolkit/harness-create.svg)](https://agentmods.dev/skills/nnabuuu/harness-engineering-toolkit/harness-create)
Your own site
<a href="https://agentmods.dev/skills/nnabuuu/harness-engineering-toolkit/harness-create"><img src="https://agentmods.dev/badge/skills/nnabuuu/harness-engineering-toolkit/harness-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00145 $0.02479
Opus 5 $0.00072 $0.01239
Sonnet 5 $0.00029 $0.00496
Haiku 4.5 $0.00015 $0.00248

Measured 5d ago against content hash 7e2fd7f43857, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-create 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 5d 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.

harness-create/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Creator

Turn a goal into a running overnight harness — from interview through spec to generated project.

Self-Review Checklist (read BEFORE and AFTER every phase)

Planning Phase Guards

  • Did NOT generate any files (harness.sh, prompts/, drafts/) during Phase 1
  • Completed ALL interview questions before producing HARNESS_SPEC.md
  • Got explicit user confirmation before moving to Phase 2

Build Phase Guards

  • Agent prompt(s) have fresh context warning at top
  • --allowedTools set for each claude -p invocation
  • Git commits after each step in the orchestrator
  • All exit conditions from the spec are implemented
  • Orchestrator supports --dry-run, --resume, --max-cost, --step, --status, --register-dagu, --unregister-dagu
  • Generator writes changelog to a dedicated FILE (not stdout)
  • Evaluator writes report to a dedicated FILE (not stdout)
  • Orchestrator extracts data from files (not stdout)
  • Orchestrator uses state.json for sub-step tracking (jq dependency checked)
  • Orchestrator injects starting-point context per iteration
  • dag.yaml generated with steps matching harness.sh step functions
  • DAGU auto-registration attempted (symlink if dagu installed, skip if not)
  • [Code Mode] Validation step with revert on failure
  • [Code Mode] Frozen file violation gate
  • [Code Mode] Regression detection (revert if score drops > 5)
  • [Investigation Mode] Investigator writes to evidence/h{N}-{name}.md
  • [Investigation Mode] Explicit CONFIRMED/ELIMINATED/INCONCLUSIVE judgment
  • [Investigation Mode] Dead-end detection when all hypotheses eliminated
  • Orchestrator has preflight() checking all prerequisites from SPEC.md
  • [If health checks defined] Orchestrator has health_check() between iterations

Entry Point Detection

Determine which entry point applies:

Entry A — No spec exists: The user has a goal but no HARNESS_SPEC.md. Start with Phase 1 (Planning Interview).

Read the full file on GitHub · 222 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 222 lines · 145 tokens per session scan A 7e2fd7f43857

Subscribe to this mod's changes

harness-create is a skill published in the GitHub repository nnabuuu/harness-engineering-toolkit (5 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 2,479 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

specification-writing

Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

overleaf-sync

Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens