qc-specialist-3

qc-specialist-3 is an agent for Claude Code from btspoony/mstar-harness. It costs 32 tokens per session (589 once invoked), scanned A, a copy of qc-specialist-2, MIT.

A review role for the third quality-control reviewer, focused on code changes, logic, performance, and reliability. It is a code-review role, not a test-running role.

In plain words
What is it for?
Use it to review diffs for logical errors, performance problems, and reliability risks. It is intended for the third reviewer in the Morning Star review process.
Why use it?
It separates independent review of the code and its risks from actually executing tests. The role also directs the agent to the broader workflow and role instructions it must read first.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the morning-star-harness plugin — 23 skills, 5 commands, 14 agents, 2 hooks shipped together

Good fit Use it to review diffs for logical errors, performance problems, and reliability risks. It is intended for the third reviewer in the Morning Star review process.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/btspoony/mstar-harness/qc-specialist-3
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/btspoony/mstar-harness

Made for: Claude Code.

Or install morning-star-harness, the plugin that ships this one along with the rest of its 23 skills, 5 commands, 14 agents, 2 hooks.

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 qc-specialist-3

README.md
[![agentmods](https://agentmods.dev/badge/agents/btspoony/mstar-harness/qc-specialist-3/github.svg)](https://agentmods.dev/agents/btspoony/mstar-harness/qc-specialist-3)
Your own site
<a href="https://agentmods.dev/agents/btspoony/mstar-harness/qc-specialist-3"><img src="https://agentmods.dev/badge/agents/btspoony/mstar-harness/qc-specialist-3/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 qc-specialist-3

Your own site · 80×15
<a href="https://agentmods.dev/agents/btspoony/mstar-harness/qc-specialist-3"><img src="https://agentmods.dev/badge/agents/btspoony/mstar-harness/qc-specialist-3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 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 97% copy Near-identical to another mod 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 $0.00032 $0.00589
Opus 5 $0.00016 $0.00295
Sonnet 5 $0.00006 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 7d ago against content hash 95f77f06835e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

qc-specialist-3 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 7d 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.

Origin

This is a copy

97% identical to qc-specialist-2 — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/qc-specialist-3.md · 61 lines

What it actually says

Morning Star Role Binding

You are qc-specialist-3. The complete role prompt is provided by the mstar-roles skill.

  • Skill: mstar-roles skill
  • Role reference: references/qc-specialist-shared.md in the mstar-roles skill
  • Role parameters: role_id=qc-specialist-3, reviewer_index=3, focus=performance_reliability, report_suffix=qc3

Mandatory First Steps

This file is a routing shell — NOT your complete role prompt. Before any work, load in order:

  1. skillmstar-harness-core (state machine, gates, routing — global SSOT)
  2. skillmstar-roles (role mapping & parameter table)
  3. Readreferences/qc-specialist-shared.md listed above

System reminders like "ALREADY LOADED" refer to prior sessions — you MUST load these for THIS session.

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. 7d ago Changed · -2 lines · -30 tokens per session 95f77f06835e
  2. 11d ago First seen · 63 lines · 62 tokens per session scan A b0377c6cf047

Subscribe to this mod's changes

qc-specialist-3 is an agent published in the GitHub repository btspoony/mstar-harness (58 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 589 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to qc-specialist-2, differing in 8 lines, and is treated as a copy.