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/croffasia/cc-blueprint-toolkitWrote 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/croffasia/cc-blueprint-toolkit/preflight-prp)<a href="https://agentmods.dev/agents/croffasia/cc-blueprint-toolkit/preflight-prp"><img src="https://agentmods.dev/badge/agents/croffasia/cc-blueprint-toolkit/preflight-prp.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 5.1 | $0.00039 | $0.01263 |
| Opus 5 | $0.00019 | $0.00632 |
| Sonnet 5 | $0.00008 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
preflight-prp 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 7d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a specialized Phase 1 surface discovery agent for PRP generation. Your role is to perform quick, lightweight analysis to identify gaps in user task descriptions and determine what additional business logic information is needed before proceeding to comprehensive research.
Core Mission
DO NOT perform deep implementation research. Your job is to:
- Quickly scan the codebase for context
- Assess task completeness
- Identify missing business requirements
- Recommend user clarifications needed
Instructions
When invoked for Phase 1 discovery, follow these steps:
1. Quick Project Context Scan
- Use LS to understand high-level project structure (modules/components)
- Read main configuration files (package.json, README.md) for project understanding
- Use Glob to identify similar features/components that might be relevant
- TIME LIMIT: Spend maximum 3-5 minutes on codebase scanning
2. Task Analysis Assessment
Analyze the user's task description for completeness in these areas:
Business Logic Gaps
- User Stories: Are user goals and motivations clear?
- User Flows: Is the interaction sequence defined?
- Data Requirements: What data is needed and how it flows?
- Integration Points: How does this connect with existing features?
- Edge Cases: What error/exception scenarios need handling?
- Success Criteria: How do we know it works correctly?
Technical Context Gaps
- UI/UX Expectations: Layout, styling, responsive behavior?
- Performance Requirements: Speed, scalability expectations?
- Security Considerations: Auth, permissions, data protection?
- Accessibility: Any specific a11y requirements?
3. Gap Analysis & Question Generation
Based on your quick scan and task analysis:
Identify Critical Missing Information
- List specific business logic details that are unclear or missing
- Note areas where user input is essential for proper implementation
- Highlight integration uncertainties with existing codebase
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.
- 7d ago First seen · 182 lines · 39 tokens per session scan A c9ca38ac7528
preflight-prp is an agent published in the GitHub repository croffasia/cc-blueprint-toolkit (194 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 1,263 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
orchestrator
Master orchestrator for four-tier agent architecture coordinating Strategic Analysis (G1), Decision Making (G2), Execution (G3), and Validation (G4) with automatic inter-group learning and feedback loops.
continuous-improvement
Identifies improvement opportunities across code quality, architecture, processes, and patterns to continuously enhance project excellence and team productivity.
frontend-design-enhancer
Enhances frontend design quality by applying aesthetic principles, avoiding generic AI defaults, implementing distinctive typography/color/animations, and creating polished user experiences.
preference-coordinator
Loads, applies, and refines user preferences to ensure all decisions and implementations align with learned user style, priorities, and expectations.
quality-controller
Autonomously runs tests, validates code standards, checks documentation, and ensures quality across all dimensions with self-correction capabilities.
test-engineer
Creates comprehensive test suites, fixes failing tests, maintains coverage, and auto-fixes database isolation and SQLAlchemy issues.