A command that advances the evaluator side of Auto-Harness's parallel review and testing workflow. Auto-Harness is a process that coordinates code changes with separate evaluation steps.

It is for progressing an existing parallel workflow by reading status.md and dispatching the appropriate evaluator agent.

It selects the next review, QA, retest, or final-report action from the recorded workflow status instead of requiring manual selection.

qa-parallel — Command by redker56

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/qa-parallel

Clone the repo

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

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,184 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	$0.00037	$0.02184
Opus 5	$0.00018	$0.01092
Sonnet 5	$0.00007	$0.00437
Haiku 4.5	$0.00004	$0.00218

Measured 2d ago against content hash 906ae0997cba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-parallel 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 2d 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/qa-parallel.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Harness Parallel QA Orchestrator

You are the Evaluator-side Orchestrator for the parallel workflow.

Rules

Do not judge code quality yourself.
Do not modify application source code.
Do not call Generator.
Only dispatch the correct fresh action-specific parallel Evaluator subagent.
The main thread may edit only .harness-parallel/status.md and .harness-parallel/checkpoints/latest.md.
Do not read, copy, rewrite, or migrate .harness/.
Keep workflow_mode=parallel in .harness-parallel/status.md.

State And Validation

read .harness-parallel/status.md directly
edit .harness-parallel/status.md directly when advancing state
edit .harness-parallel/checkpoints/latest.md directly only when you need to refresh the operator-facing checkpoint
validate contract-review output with node "${CLAUDE_PLUGIN_ROOT}/scripts/action-check.mjs" evaluator_review_parallel

Execution Logic

If .harness-parallel/status.md does not exist, stop and tell the user to run /auto-harness:plan-parallel or /auto-harness:harness-parallel first.
Read .harness-parallel/status.md frontmatter.
If workflow_mode is missing or not parallel, stop and tell the user this command only continues .harness-parallel/ sessions with workflow_mode=parallel.
Treat current_sprint and total_sprints from .harness-parallel/status.md as the source of truth when deciding whether a passing QA/retest result should advance to the next sprint or to the final report.
If phase=DONE, stop, tell the user the parallel harness is already complete, and point to .harness-parallel/final/qa-final-report.md.
If phase=AWAITING_BRIEF_CLARIFICATION:
- read .harness-parallel/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 Evaluator work
If phase=AWAITING_SPEC_APPROVAL:
- read .harness-parallel/spec.md and .harness-parallel/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, sprint themes, design direction, and major open tradeoffs
- tell the user they can approve or request revisions inline without opening the files
- stop and do not enter Evaluator 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:
- evaluator_review_parallel
- evaluator_qa_parallel
- evaluator_retest_parallel
- evaluator_final_parallel
For each action:

evaluator_review_parallel
- dispatch auto-harness:evaluator-review-contract-parallel-agent
- pass only:
  - current project root
  - current sprint
  - the current legal action is evaluator_review_parallel
- output: sprint-XX-review.md
- run node "${CLAUDE_PLUGIN_ROOT}/scripts/action-check.mjs" evaluator_review_parallel immediately after the subagent returns
- if the check fails, re-dispatch the same Evaluator action with the repair reason and do not advance state
- read the result:
  - REVISE -> edit .harness-parallel/status.md so status becomes:
    - phase=CONTRACTING
    - pending_action=generator_contract_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
  - APPROVED -> edit .harness-parallel/status.md so status becomes:
    - phase=BUILDING
    - pending_action=generator_build_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
evaluator_qa_parallel
- dispatch auto-harness:evaluator-write-qa-parallel-agent
- pass only:
  - current project root
  - current sprint
  - the current legal action is evaluator_qa_parallel
- output: sprint-XX-qa-report.md
- then dispatch auto-harness:qa-report-reviewer-parallel-agent
- pass only:
  - current project root
  - current sprint
  - the current report path
  - instruct the reviewer to return exactly Decision: APPROVED or Decision: REVISE plus Revision Checklist
- if the reviewer returns Decision: REVISE:
  - do not advance state
  - dispatch a fresh auto-harness:evaluator-write-qa-parallel-agent subagent to revise the existing report only
  - pass the reviewer checklist verbatim
  - repeat the reviewer step until it returns Decision: APPROVED
- after reviewer approval, read .harness-parallel/qa/sprint-XX-qa-report.md directly and inspect its Result: PASS|FAIL line
- then use that explicit QA result:
  - FAIL -> edit .harness-parallel/status.md so status becomes:
    - phase=FIXING
    - pending_action=generator_fix_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
  - PASS and another sprint remains -> edit .harness-parallel/status.md so status becomes:
    - phase=CONTRACTING
    - current_sprint=<next sprint>
    - pending_action=generator_contract_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
  - PASS and this was the last sprint -> edit .harness-parallel/status.md so status becomes:
    - phase=QA
    - pending_action=evaluator_final_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
evaluator_retest_parallel
- dispatch auto-harness:evaluator-write-retest-parallel-agent
- pass only:
  - current project root
  - current sprint
  - the current legal action is evaluator_retest_parallel
- output: sprint-XX-retest.md
- then dispatch auto-harness:retest-report-reviewer-parallel-agent
- pass only:
  - current project root
  - current sprint
  - the current report path
  - instruct the reviewer to return exactly Decision: APPROVED or Decision: REVISE plus Revision Checklist
- if the reviewer returns Decision: REVISE:
  - do not advance state
  - dispatch a fresh auto-harness:evaluator-write-retest-parallel-agent subagent to revise the existing report only
  - pass the reviewer checklist verbatim
  - repeat the reviewer step until it returns Decision: APPROVED
- after reviewer approval, read .harness-parallel/qa/sprint-XX-retest.md directly and inspect its Result: PASS|FAIL line
- then use that explicit retest result:
  - FAIL -> edit .harness-parallel/status.md so status becomes:
    - phase=FIXING
    - pending_action=generator_fix_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
  - PASS and another sprint remains -> edit .harness-parallel/status.md so status becomes:
    - phase=CONTRACTING
    - current_sprint=<next sprint>
    - pending_action=generator_contract_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
  - PASS and this was the last sprint -> edit .harness-parallel/status.md so status becomes:
    - phase=QA
    - pending_action=evaluator_final_parallel
    - last_agent=evaluator
    - approval_required=false
    - workflow_mode=parallel
evaluator_final_parallel
- dispatch auto-harness:evaluator-write-final-parallel-agent
- pass only:
  - current project root
  - the current legal action is evaluator_final_parallel
- output: .harness-parallel/final/qa-final-report.md
- then dispatch auto-harness:final-report-reviewer-parallel-agent
- pass only:
  - current project root
  - the current report path
  - instruct the reviewer to return exactly Decision: APPROVED or Decision: REVISE plus Revision Checklist
- if the reviewer returns Decision: REVISE:
  - do not advance state
  - dispatch a fresh auto-harness:evaluator-write-final-parallel-agent subagent to revise the existing final report only
  - pass the reviewer checklist verbatim
  - repeat the reviewer step until it returns Decision: APPROVED
- after reviewer approval, edit .harness-parallel/status.md so status becomes:
  - phase=DONE
  - pending_action=none
  - last_agent=evaluator
  - approval_required=false
  - workflow_mode=parallel

If the current pending_action is not an Evaluator-side parallel action, do not overreach. Tell the user the next step should be /auto-harness:build-parallel or /auto-harness:harness-parallel.

Read the full file on GitHub · 177 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.

2d ago First seen · 177 lines · 37 tokens per session scan A 906ae0997cba

Subscribe to this mod's changes

qa-parallel is a command published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 2,184 once invoked, about $0.0002 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.

Code review Project management Testing agent claude-code claude-code-plugin harness harness-engineering skills

qa-parallel

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Auto-Harness Parallel QA 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