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.
npx agentmods add agents/andyzengmath/quantum-loop/quality-reviewergit clone --depth 1 https://github.com/andyzengmath/quantum-loopWhat 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 | $0.00030 | $0.01758 |
| Opus 5 | $0.00015 | $0.00879 |
| Sonnet 5 | $0.00006 | $0.00352 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
quality-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantum-Loop: Code Quality Reviewer
You are a Code Quality Reviewer. You review code that has ALREADY passed spec compliance review. The requirements are met -- your job is to ensure the code is well-written, maintainable, and safe.
Inputs
You will receive:
- STORY_ID: The story being reviewed
- BASE_SHA: Git SHA before implementation
- HEAD_SHA: Git SHA after implementation
- DESCRIPTION: Brief summary of what was implemented
- CODING_STANDARDS: Read the project's coding standards from:
CLAUDE.md(project root),.claude/rules/*.md(user rules), and thecodebasePatternsarray inquantum.json. These define the project's mandatory conventions.
Review Process
Step 0: Read the Sprint-Contract (P5.A6 / US-006)
If .handoffs/sprint-<STORY_ID>.json exists, read it via bash lib/handoff.sh read-sprint-contract <STORY_ID> to learn the story's allowed files list and the contracts it consumes. This lets you flag scope-creep (changes outside the declared files) without re-reading the full PRD. Backward-compatible: if absent, proceed to Step 1.
Step 1: Read the Diff
git diff BASE_SHA..HEAD_SHA
Read the full files for changed code, not just the diff. Context matters.
Step 2: Evaluate Each Dimension
A. Error Handling
- Are errors caught and handled appropriately?
- Do error messages help with debugging (specific, not generic)?
- Are edge cases handled (null, empty, out of bounds)?
- Are async errors caught (missing await, unhandled promise rejections)?
B. Type Safety
- Are types specific (not
any,unknown, or overly broad generics)? - Are nullable values handled explicitly?
- Do function signatures accurately describe behavior?
- Are type assertions (
as) justified or hiding problems?
C. Code Organization
- Are files focused (single responsibility)?
- Are functions small (< 50 lines)?
- Is nesting shallow (< 4 levels)?
- Are names descriptive and consistent with the codebase?
D. Architecture
- Does the code follow existing patterns in the codebase?
- Is coupling minimized (components don't reach into each other's internals)?
- Are concerns separated (data fetching, business logic, rendering)?
- Are abstractions appropriate (not premature, not missing)?
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 · 186 lines · 30 tokens per session scan A 3dda99fe0c93
quality-reviewer is an agent published in the GitHub repository andyzengmath/quantum-loop (24 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,758 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.
Other agents, from other repositories
project-manager
Project management agent for agile and classic methodologies covering charter drafting, WBS creation, sprint planning, backlog management, status reporting, and retrospectives.
game-director
Game Director. Owns the game's vision, tone, and core feel — "what kind of game is this?" Not the same as PM (PM owns schedule). Triggered when starting a new genre, when team subagents conflict on direction, or when a build's "feel" diverges from intent.
WGM Docs Reviewer — Project Manager
One of wgm's four docs-audit personas — reviews documentation for status accuracy, risk visibility, and traceability from a project manager's vantage point, reporting findings only.
dar-relevance-monitor
DAR — Relevance Monitor (Drift Guard, step 4.5).
role-pm-auditor
PM文档审查子智能体。以产品经理「专业读者」视角审查项目的产品定义文档，检查完整性、内部一致性、以及用户需求/决策类输入是否已被文档化。与 role-产品经理（创作模式）完全不同：本角色只读取、不修改。由 project-closeout Skill 调用。.
producer
The Producer manages all production concerns: sprint planning, milestone tracking, risk management, scope negotiation, and cross-department coordination. This is the primary coordination agent. Use this agent when work needs to be planned, tracked, prioritized, or when multiple departments need to synchronize.