A command that advances the build side of an Auto-Harness project by choosing the needed contract, build, or fix action from the project's status file. Auto-Harness is a workflow for coordinating code generation and evaluation.

Use it to start or continue a sprint's generator work, or to apply the next required fix when the project is in a supported harness phase.

It keeps the build process moving according to the recorded project state and checks that the generator produced the expected kind of result.

build — Command for coding agents by redker56: A command that advances the build side of an…

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 commands/redker56/auto-harness/build

Clone the repo

git clone --depth 1 https://github.com/redker56/auto-harness

Or install auto-harness, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/redker56/auto-harness/build.svg)](https://agentmods.dev/commands/redker56/auto-harness/build)

Your own site

<a href="https://agentmods.dev/commands/redker56/auto-harness/build"><img src="https://agentmods.dev/badge/commands/redker56/auto-harness/build.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 1,124 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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.01124
Opus 5	$0.00015	$0.00562
Sonnet 5	$0.00006	$0.00225
Haiku 4.5	$0.00003	$0.00112

Measured 3d ago against content hash e13ca1fec56b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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 3d 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.

commands/build.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Harness Build Orchestrator

You are the Generator-side Orchestrator.

Rules

Do not write source code yourself.
Do not perform QA judgment.
Do not call Evaluator.
Only dispatch the correct fresh action-specific Generator subagent.
The main thread may edit only .harness/status.md and .harness/checkpoints/latest.md.

State And Validation

read .harness/status.md directly
edit .harness/status.md directly when advancing state
edit .harness/checkpoints/latest.md directly only when you need to refresh the operator-facing checkpoint
validate generator outputs with node "${CLAUDE_PLUGIN_ROOT}/scripts/action-check.mjs" generator_contract, generator_build, or generator_fix

Execution Logic

If .harness/status.md does not exist, stop and tell the user to run /auto-harness:plan or /auto-harness:harness first.
Read .harness/status.md frontmatter.
If phase=DONE, stop, tell the user the harness is already complete, and point to .harness/final/qa-final-report.md.
If phase=AWAITING_BRIEF_CLARIFICATION:
- read .harness/intake.md
- restate the clarification questionnaire directly in chat
- tell the user they can answer inline without opening the file
- stop and do not enter Generator work
If phase=AWAITING_SPEC_APPROVAL:
- read .harness/spec.md and .harness/design-direction.md
- restate the approval summary directly in chat, including:
  - product overview
  - goals and non-goals
  - locked architecture and stack choices
  - total sprint count and sprint themes
  - design direction:
    - product mood and visual principles
    - layout and interaction direction
    - anti-patterns to avoid
  - any major open tradeoffs
- tell the user they can approve or request revisions inline without opening the files
- stop and do not enter Generator work
If the user provided a sprint number:
- only proceed when it matches the current legal state
- do not skip unfinished sprints
Only handle these pending_action values:
- generator_contract
- generator_build
- generator_fix
For each action:
- generator_contract
  - dispatch auto-harness:generator-draft-contract-agent
  - pass only:
    - current project root
    - current sprint
    - the current legal action is generator_contract
  - output: sprint-XX-contract.md
- run node "${CLAUDE_PLUGIN_ROOT}/scripts/action-check.mjs" generator_contract immediately after the subagent returns
- if the check fails, re-dispatch the same Generator action with the repair reason and do not advance state
- then edit .harness/status.md so status becomes:
  - phase=CONTRACTING
  - pending_action=evaluator_review
  - last_agent=generator
  - approval_required=false
- generator_build
  - dispatch auto-harness:generator-build-sprint-agent
  - pass only:
    - current project root
    - current sprint
    - the current legal action is generator_build
  - outputs: code, .harness/runtime.md, .harness/qa/sprint-XX-self-check.md
- run node "${CLAUDE_PLUGIN_ROOT}/scripts/action-check.mjs" generator_build immediately after the subagent returns
- if the check fails, re-dispatch the same Generator action with the repair reason and do not advance state
- then edit .harness/status.md so status becomes:
  - phase=QA
  - pending_action=evaluator_qa
  - last_agent=generator
  - approval_required=false
- generator_fix
  - dispatch auto-harness:generator-apply-fixes-agent
  - pass only:
    - current project root
    - current sprint
    - the current legal action is generator_fix
  - outputs: fixes and .harness/qa/sprint-XX-fix-log.md
- run node "${CLAUDE_PLUGIN_ROOT}/scripts/action-check.mjs" generator_fix immediately after the subagent returns
- if the check fails, re-dispatch the same Generator action with the repair reason and do not advance state
- then edit .harness/status.md so status becomes:
  - phase=QA
  - pending_action=evaluator_retest
  - last_agent=generator
  - approval_required=false
If the current pending_action is not a Generator-side action, do not overreach. Tell the user the next step should be /auto-harness:qa or /auto-harness:harness.

Read the full file on GitHub · 101 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.

3d ago First seen · 101 lines · 29 tokens per session scan A e13ca1fec56b

Subscribe to this mod's changes

build is a command published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,124 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.

agent claude-code claude-code-plugin harness harness-engineering skills

build

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Auto-Harness Build Orchestrator

Rules

State And Validation

Execution Logic

What this file has done since we first saw it

Other commands, from other repositories

planwt

statuswt

finishwt

release

review-and-fix

takeoff