Borrowing it
Nothing to install: this file belongs to Kandil7/prprompts-flutter-generator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kandil7/prprompts-flutter-generator/master/.claude/commands/prd/refine.mdgit clone --depth 1 https://github.com/Kandil7/prprompts-flutter-generatorWrote 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/commands/kandil7/prprompts-flutter-generator/refine)<a href="https://agentmods.dev/commands/kandil7/prprompts-flutter-generator/refine"><img src="https://agentmods.dev/badge/commands/kandil7/prprompts-flutter-generator/refine.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 | $0.00018 | $0.03522 |
| Opus 5 | $0.00009 | $0.01761 |
| Sonnet 5 | $0.00004 | $0.00704 |
| Haiku 4.5 | $0.00002 | $0.00352 |
Grade A, and why
Refine 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 6d 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 — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine Product Requirements Document
Overview
Analyze the existing PRD and guide the user through an iterative refinement process to improve completeness, clarity, feasibility, and security. This is an interactive loop that identifies weak areas and helps strengthen them through targeted questions and suggestions.
Input File
Look for: docs/PRD.md
Refinement Process
Step 1: Initial Quality Assessment
Run comprehensive analysis on current PRD:
Completeness Analysis (0-100%):
- Required sections present: 15/15 sections
- YAML frontmatter completeness: All required fields
- Feature detail level: User stories, acceptance criteria, technical requirements
- Compliance documentation: Match compliance array
- Non-functional requirements: Performance, security, accessibility
- Score Calculation: (Present sections / Expected sections) × 100
Clarity Analysis (0-100%):
- Ambiguous language detection: "maybe", "possibly", "might", "could be"
- Measurable acceptance criteria: Quantified vs vague
- Clear priorities: P0/P1/P2 vs unclear
- Concrete timelines: Specific dates vs "soon", "later"
- Well-defined success metrics: SMART criteria
- Score Calculation: (Clear criteria / Total criteria) × 100
Feasibility Analysis (0-100%):
- Timeline vs complexity: Story points / available weeks
- Team size vs scope: Features / team members / weeks
- Technology maturity: Proven vs bleeding-edge
- Dependency risks: External APIs, third-party services
- Resource availability: Realistic team composition
- Score Calculation: Weighted average of sub-factors
Security Analysis (0-100%):
- Compliance coverage: Required vs specified standards
- Auth/AuthZ patterns: Complete implementation plan
- Data protection: Encryption at rest and in transit
- Audit logging: For sensitive data access
- Security testing: Pen testing, security reviews planned
- Score Calculation: (Security requirements met / Total requirements) × 100
Calculate Overall Grade:
- A (90-100%): Production-ready PRD
- B (80-89%): Strong PRD, minor improvements needed
- C (70-79%): Good foundation, significant improvements needed
- D (60-69%): Major gaps, substantial work required
- F (<60%): Not ready for PRPROMPTS generation
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.
- 6d ago First seen · 467 lines · 18 tokens per session scan A e9d5fdaaad20
Refine PRD is a command published in the GitHub repository Kandil7/prprompts-flutter-generator (11 stars, last pushed 9mo ago), licensed MIT. It adds 18 tokens to every session and 3,522 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 commands, from other repositories
speckit.bug.fetch
Load an existing GitHub issue into the bug workflow (the complement of bug.issue) and seed a triage draft.
speckit.chore.fetch
Load an existing GitHub issue into the chore workflow and seed a triage draft.
speckit.chore.implement
Implement the scoped chore (the actual maintenance work) and record what changed.
speckit.bug.pr
Open a pull request for the applied bug fix, linking the tracked issue.
speckit.gh-triage.feature
Create a GitHub issue describing a new feature, label it with the configured feature label, and optionally auto-run speckit.specify to turn it into a spec.
speckit.md-doctor.drift
Re-evaluate since the last run: compute the git/.memsearch/TDD delta, re-score previously graded files in light of what changed, and report which past suggestions were resolved or are now stale/false.