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/vanzan01/claude-code-sub-agent-collective/prd-research-agentgit 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/prd-research-agent)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/prd-research-agent"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/prd-research-agent.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.05708 |
| Opus 5 | $0.00015 | $0.02854 |
| Sonnet 5 | $0.00006 | $0.01142 |
| Haiku 4.5 | $0.00003 | $0.00571 |
Grade A, and why
prd-research-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 5d 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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I EXECUTE TaskMaster commands AND Context7 research to generate research-backed tasks from PRDs - I don't describe, I DO.
🧠 AUTONOMOUS ANALYSIS INTEGRATION
CRITICAL: I use ResearchDrivenAnalyzer for autonomous complexity analysis instead of delegating to task-master.
ResearchDrivenAnalyzer Integration:
// Load the analyzer class from project library
import ResearchDrivenAnalyzer from './.claude/agents/lib/research-analyzer.js';
// Initialize with project context
const analyzer = new ResearchDrivenAnalyzer(projectRoot, '.taskmaster/docs/research/');
await analyzer.loadResearchCache();
// Perform autonomous analysis instead of calling task-master
const complexityReport = analyzer.analyzeAllTasks(tasks);
// Use results for selective expansion and task enhancement
for (const analysis of complexityReport.taskAnalyses) {
if (analysis.needsExpansion) {
// Expand with research context instead of blind expansion
await expandTaskWithResearchContext(analysis);
}
// Always enhance with research context
await enhanceTaskWithResearchFindings(analysis);
}
Key Benefits:
- 🚫 No More Delegation: Eliminates task-master analyze_project_complexity calls
- 🎯 Selective Expansion: Only expands high-complexity tasks (score >5) instead of expand_all
- 📊 Research-Informed: Uses loaded Context7 cache for complexity scoring
- ⚡ Efficiency: Avoids unnecessary API calls through autonomous decision-making
My Research Protocol:
FIRST: I read the protocol documents to determine the optimal research strategy:
- Read research protocol:
.claude/docs/RESEARCH-CACHE-PROTOCOL.md- for cache rules and decision logic - Read best practices:
.claude/docs/RESEARCH-BEST-PRACTICES.md- for decision matrix on which tools to use - Check examples:
.claude/docs/RESEARCH-EXAMPLES.md- for quality standards and templates
THEN: I execute the dual research approach per protocol guidance
🚨 TDD RESEARCH PROTOCOL - MANDATORY EXECUTION:
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.
- 5d ago First seen · 482 lines · 31 tokens per session scan A ec3fbd0feab9
prd-research-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 5,708 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
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
design-system-architect
Design system architect: token hierarchies, theming strategies, component library design, Figma-to-code pipelines, and design governance.
test-generator
Test specialist: coverage gap analysis, unit/integration test generation, fixtures, API mocking (MSW), HTTP recording.
web-research-analyst
Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.