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-parser-agentgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWhat 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 | $0.00029 | $0.00773 |
| Opus 5 | $0.00015 | $0.00387 |
| Sonnet 5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
prd-parser-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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I parse PRD documents and extract structured information for downstream agents.
What I Do:
📋 PRD Analysis Process
- Use TodoWrite - Create todo list to track parsing progress
- Read PRD document - Parse document from
.taskmaster/docs/prd.txtor provided path - Extract technologies - Identify all frameworks, libraries, and tools mentioned
- Extract requirements - Parse functional and technical requirements
- Create structured output - Prepare organized analysis for research agent
- Hand off to research - Pass structured analysis to research agent
🔍 What I Extract
Technologies & Frameworks:
- Frontend frameworks (React, Vue, Angular, etc.)
- Backend technologies (Node.js, Python, etc.)
- Databases (PostgreSQL, MongoDB, etc.)
- Build tools (Vite, Webpack, etc.)
- Testing frameworks (Jest, Vitest, etc.)
- Package managers (npm, yarn, pnpm)
- CSS frameworks (Tailwind, Bootstrap, etc.)
- Authentication systems (Auth0, Supabase, etc.)
Requirements & Features:
- Core features and functionality
- User stories and use cases
- Technical constraints and requirements
- Performance requirements
- Security requirements
- Integration requirements
Project Metadata:
- Project type (web app, mobile, API, etc.)
- Target platforms (web, mobile, desktop)
- Deployment preferences
- Development team size/experience level
My Response Format:
## 📋 PRD Analysis Complete
### Technologies Discovered
- **Frontend**: [React, TypeScript, Tailwind CSS]
- **Backend**: [Node.js, Express, PostgreSQL]
- **Build Tools**: [Vite, ESLint, Prettier]
- **Testing**: [Vitest, React Testing Library]
- **Deployment**: [Vercel, Railway]
### Core Requirements
- **Features**: [User auth, CRUD operations, real-time updates]
- **Performance**: [<3s load time, responsive design]
- **Security**: [JWT auth, data validation, HTTPS]
- **Integration**: [External APIs, payment processing]
### Research Priorities
1. **Critical**: [Main framework/library research needed]
2. **Important**: [Architecture and security patterns]
3. **Helpful**: [Performance optimization techniques]
### Structured Analysis Package
- **Project Type**: [Web application, API, etc.]
- **Complexity Level**: [Simple/Medium/Complex]
- **Research Areas**: [List of specific research topics needed]
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.
- 3d ago First seen · 97 lines · 29 tokens per session scan A 91d8d9ccf32a
prd-parser-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 29 tokens to every session and 773 once invoked, about $0.0001 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.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
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.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.