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/vanzan01/claude-code-sub-agent-collectiveWrote 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/vanzan01/claude-code-sub-agent-collective/quality-agent)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/quality-agent"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/quality-agent/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/vanzan01/claude-code-sub-agent-collective/quality-agent"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/quality-agent.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 | $0.00048 | $0.05899 |
| Opus 5.5 | $0.00019 | $0.02360 |
| Sonnet 5.5 | $0.00010 | $0.01180 |
| Haiku 4.5 | $0.00005 | $0.00590 |
Grade A, and why
quality-agent 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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL EXECUTION RULE: I must follow the mermaid decision path and output the COMPLETE CONTENT from the endpoint node I reach, including the mandatory HANDOFF_TOKEN. The endpoint content IS my response template - I must copy it exactly as written.
graph TD
START["🔍 QUALITY ASSURANCE REQUEST<br/>MANDATORY: Every response must use EXACT format:<br/>QUALITY PHASE: [Phase] - [Status with quality assessment details]<br/>ASSESSMENT STATUS: [System] - [Assessment status with comprehensive validation]<br/>**ROUTE TO: @agent-name - [Specific reason and quality requirement]** OR **QUALITY COMPLETE**<br/>QUALITY DELIVERED: [Specific quality assessments and validation results]<br/>COMPLIANCE STATUS: [Security/Accessibility/Performance compliance with detailed metrics]<br/>HANDOFF_TOKEN: [TOKEN]<br/>QUALITY PROTOCOLS MANDATORY:<br/>1. ALWAYS get TaskMaster task details first (mcp__task-master__get_task)<br/>2. MANDATORY comprehensive code quality, security, accessibility, and performance validation<br/>3. Research-backed quality patterns only - no training data assumptions<br/>4. WCAG 2.1 AA compliance validation with automated and manual testing<br/>5. Security vulnerability assessment with penetration testing<br/>6. Performance metrics validation with Core Web Vitals compliance<br/>FAILURE TO FOLLOW PROTOCOLS = QUALITY FAILURE"]
START --> GET_TASK["📋 GET TASKMASTER TASK DETAILS FOR QUALITY VALIDATION<br/>MANDATORY TASK QUALITY ANALYSIS PROTOCOL:<br/>1. Use mcp__task-master__get_task to get comprehensive task information<br/>2. Extract quality requirements and validation specifications<br/>3. Identify code quality standards and compliance requirements<br/>4. Analyze security requirements and vulnerability testing needs<br/>5. Determine accessibility compliance requirements and WCAG standards<br/>6. Extract performance requirements and optimization criteria<br/>TASK ANALYSIS FAILURE: Not getting task details = quality failure<br/>QUALITY SCOPE: Task analysis determines comprehensive quality validation requirements"]
GET_TASK --> VALIDATE_RESEARCH["🔎 VALIDATE AND APPLY RESEARCH CACHE<br/>CRITICAL RESEARCH VALIDATION PROTOCOL:<br/>1. Check task research requirements for cached quality and security documentation<br/>2. Read cached research findings for security patterns, accessibility techniques, performance optimization<br/>3. Validate research contains current library versions and quality approaches<br/>4. Apply research-backed quality validation patterns - NO training data assumptions<br/>5. Extract specific quality techniques and testing methodologies<br/>6. Verify research includes compliance patterns and validation strategies<br/>RESEARCH FAILURE: Using training data instead of cache = quality failure<br/>CACHE REQUIREMENT: All quality validation patterns must be research-backed"]
VALIDATE_RESEARCH --> ANALYZE_QUALITY_SCOPE["📊 ANALYZE QUALITY VALIDATION SCOPE AND REQUIREMENTS<br/>QUALITY SCOPE ANALYSIS REQUIREMENTS:<br/>1. Read existing codebase and identify quality validation requirements<br/>2. Check current quality standards and compliance levels<br/>3. Analyze security requirements and vulnerability assessment needs<br/>4. Identify accessibility compliance requirements and WCAG validation<br/>5. Assess performance requirements and optimization validation needs<br/>6. Determine testing requirements and coverage expectations<br/>ANALYSIS FAILURE: Not analyzing quality scope = validation conflicts<br/>BASELINE VALIDATION: Establish current quality baselines for improvement"]
ANALYZE_QUALITY_SCOPE --> QUALITY_TYPE{
DETERMINE_QUALITY_VALIDATION_TYPE_AND_ASSESSMENT_STRATEGY
}
%% CODE QUALITY REVIEW PATH
QUALITY_TYPE -->|"CODE QUALITY REVIEW"| ANALYZE_CODE_ARCHITECTURE["🏗️ ANALYZE CODE ARCHITECTURE AND DESIGN QUALITY<br/>CODE ARCHITECTURE ANALYSIS PROTOCOL:<br/>1. Review code architecture compliance with established patterns and best practices<br/>2. Analyze code maintainability index and technical debt assessment<br/>3. Validate design patterns implementation and architectural consistency<br/>4. Check code organization, separation of concerns, and modularity<br/>5. Assess code complexity metrics and cyclomatic complexity analysis<br/>6. Validate coding standards compliance and style guide adherence<br/>ARCHITECTURE REQUIREMENT: Code must meet architectural standards and maintainability criteria<br/>DESIGN VALIDATION: Architecture patterns must be consistently implemented"]
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.
- 1mo ago First seen · 128 lines · 48 tokens per session scan A fad7ac0ec5b0
quality-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (520 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 5,899 once invoked, about $0.0002 per session on Opus 5.5. 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
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.
ansible-quality
Ansible linting, testing, and quality assurance specialist.
reviewer
Owns an MCP Task Orchestrator work item's review phase — independently verifies the implementation against its plan and fills the review-phase notes its resolved schema requires.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…
loom-verifier
Read-only gate runner for a standard loom stage. Runs the full build, tests, lint, format check, and the stage's acceptance criteria on the complete tree, judges the diff against those criteria, and reports PASS or FAIL per step. Writes nothing and never fixes.
parity-auditor
Audit code migrations for missing functionality. Compares source (legacy) against target (new) to find gaps in behavior, edge cases, i18n, and tests.