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.
git clone --depth 1 https://github.com/charlie947/agent-harness-starterWrote 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.
[](https://agentmods.dev/agents/charlie947/agent-harness-starter/qa-scorer)<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.
<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>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 5.1 | $0.00056 | $0.00588 |
| Opus 5 | $0.00028 | $0.00294 |
| Sonnet 5 | $0.00011 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
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.
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
- Read the artifact and the brief. Both are in the handoff.
- Score against the rubric. Default rubric below. Replace with a project-specific one if the brief defines one.
- If score ≥ threshold: return PASS with the score breakdown.
- 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]
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.
- 10d ago First seen · 72 lines · 56 tokens per session scan A c90001b511bd
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.