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 commands/vrsen/openswarm/create-prdgit clone --depth 1 https://github.com/VRSEN/OpenSwarmWhat 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 | $0.00000 | $0.01069 |
| Opus 5 | $0.00000 | $0.00535 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
create-prd 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- create-prd — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Creation - Product Requirements Document for Agency Swarm
Your task is to create a Product Requirements Document (PRD) that defines the agency structure, agent roles, and tool specifications.
Step 1: Ask Questions
Ask the user for:
- Agency Name
- Purpose: What does the agency do?
- Agent Roles: What roles are needed?
- Communication Flows: How do agents communicate?
- Tools per Agent: What actions should each agent perform?
- External Integrations: What APIs or services will be used?
Step 2: Research
Search for available MCP servers for the systems user wants to connect to.
MCP Search Priority:
- Check official registry: https://github.com/mcp
- Search using web search:
mcp server <system name> - If not MCP server is found, search for API documentation and create a custom tool that wraps the API call.
Common MCP Servers:
@modelcontextprotocol/server-filesystem- File operations@modelcontextprotocol/server-github- GitHub@modelcontextprotocol/server-slack- Slack@modelcontextprotocol/server-postgres- PostgreSQL@modelcontextprotocol/server-sqlite- SQLite@modelcontextprotocol/server-puppeteer- Web automation@modelcontextprotocol/server-brave-search- Web search
Built-in Tools:
WebSearchTool- Built-in web search (use this instead of MCP for web search)
For each integration:
- Document MCP server package name if found
- Note required API keys and how to obtain them
- If no MCP exists, note that custom tool will be needed
Step 3: Create PRD
Create ./prd.txt using this template:
# [Agency Name]
---
- **Purpose:** [High-level description: what the agency achieves, target market, value proposition]
- **Communication Flows:**
- **Between Agents:**
- [Description of protocols and flows between agents, shared resources, data exchange]
- **Example Flow:**
- **[Agent A] -> [Agent B]:** [Trigger conditions, interaction description, expected outcomes]
- **[Agent B] -> [Agent C]:** [Trigger conditions, interaction description, expected outcomes]
- **Agent to User Communication:** [How agents communicate with users, interfaces, channels]
---
## [Agent Name]
### Role within the Agency
[Description of realistic job role and responsibilities - model after actual professions]
### Tools
- **[ToolName]:**
- **Description**: [What this tool does and when it's used - must be a real-world task]
- **Inputs**:
- [name] (type) - description
- **Validation**:
- [Condition] - description
- **Core Functions:** [Main functions the tool performs]
- **APIs**: [List of APIs used, if any]
- **Output**: [Expected output format - string or JSON object]
- **MCP Name**: [MCP server package name if found]
- **URL**: [Url of the server’s github / official page]
- **Authentication**: [How the MCP is authenticated]
- **Allowed Tools**: [Which tools to allow]
---
[...repeat for each agent]
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 · 137 lines · 0 tokens per session scan A 6e51c2069a14
create-prd is a command published in the GitHub repository VRSEN/OpenSwarm (2,855 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,069 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.