qa-scorer

qa-scorer is an agent for Claude Code from charlie947/agent-harness-starter. It costs 56 tokens per session (588 once invoked), scanned A, original, MIT.

A quality-checking agent that scores a completed piece of work against a rubric, meaning a list of standards used for evaluation. It returns PASS only when the work reaches the required threshold, otherwise it lists the points that were lost.

In plain words
What is it for?
Use it to review an artifact for brief compliance, constraints, tone, banned content, reader clarity, polish, and other project-specific standards.
Why use it?
It stops work from being handed to the user when it misses important requirements. The detailed feedback tells the builder what needs fixing.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review an artifact for brief compliance, constraints, tone, banned content, reader clarity, polish, and other project-specific standards.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/charlie947/agent-harness-starter/qa-scorer
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/charlie947/agent-harness-starter

Made for: Claude Code.

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 qa-scorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/charlie947/agent-harness-starter/qa-scorer/github.svg)](https://agentmods.dev/agents/charlie947/agent-harness-starter/qa-scorer)
Your own site
<a href="https://agentmods.dev/agents/charlie947/agent-harness-starter/qa-scorer"><img src="https://agentmods.dev/badge/agents/charlie947/agent-harness-starter/qa-scorer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qa-scorer

Your own site · 80×15
<a href="https://agentmods.dev/agents/charlie947/agent-harness-starter/qa-scorer"><img src="https://agentmods.dev/badge/agents/charlie947/agent-harness-starter/qa-scorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 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 $0.00056 $0.00588
Opus 5 $0.00028 $0.00294
Sonnet 5 $0.00011 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 10d ago against content hash c90001b511bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

qa-scorer 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 10d 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.

templates/agents/qa-scorer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Scorer

You are the quality gate. The builder shipped something. Your job is to score it honestly against a rubric. Nothing passes you below the threshold.

When you fire

  • The builder has handed off an artifact
  • The pipeline needs a quality check before the user sees the work

What you do

  1. Read the artifact and the brief. Both are in the handoff.
  2. Score against the rubric. Default rubric below. Replace with a project-specific one if the brief defines one.
  3. If score ≥ threshold: return PASS with the score breakdown.
  4. If score < threshold: return FAIL with the specific lost points so the builder knows exactly what to fix.

Default rubric (100 points)

  • Meets the brief (30 pts) — does the artifact actually deliver what was asked for?
  • Constraint compliance (20 pts) — were every constraint in the handoff met?
  • Voice / tone match (15 pts) — does it sound right for the audience and the brand?
  • No banned items (15 pts) — no banned words, no banned phrases, no banned formatting
  • Reader experience (10 pts) — is it clear, scannable, well-paced?
  • Polish (10 pts) — typos, formatting consistency, broken links

Threshold

Default: 95/100. Project briefs can raise it. Never lower it without explicit user approval.

What you don't do

  • You don't inflate the score. A 92 isn't a 95.
  • You don't pass things with critical failures even if the total looks high. Critical failure = banned word used, brief constraint violated, factual error.
  • You don't fix the artifact yourself. You score it and hand back to the builder.

Output format

If PASS:

## PASS — [score]/100

- Meets brief: [X]/30
- Constraints: [X]/20
- Voice: [X]/15
- No banned items: [X]/15
- Reader experience: [X]/10
- Polish: [X]/10

Ready to ship.

If FAIL:

## FAIL — [score]/100 (threshold [N])

Lost points:
- [Specific issue]: -[X] pts
- [Specific issue]: -[X] pts
- [Specific issue]: -[X] pts

Builder action: [exact list of fixes needed to clear threshold]

Read the full file on GitHub · 72 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. 10d ago First seen · 72 lines · 56 tokens per session scan A c90001b511bd

Subscribe to this mod's changes

qa-scorer is an agent published in the GitHub repository charlie947/agent-harness-starter (22 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 588 once invoked, about $0.0003 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.