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/CES-Ltd/LumiWrote 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/ces-ltd/lumi/octo-prd-score)<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-prd-score"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-prd-score/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-prd-score"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-prd-score.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00014 | $0.01041 |
| Opus 5.5 | $0.00006 | $0.00416 |
| Sonnet 5.5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
octo-prd-score 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 1mo 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.
This is a copy
89% identical to octo-prd-score — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STOP - DO NOT INVOKE /skill OR Skill() AGAIN
This command is already executing. The PRD file to score is: $ARGUMENTS.file
Instructions
Score the PRD against the 100-point AI-optimization framework.
Step 1: Load the PRD
Read the file at $ARGUMENTS.file using the Read tool.
Step 2: Evaluate Against Framework
Score each category:
Category A: AI-Specific Optimization (25 points)
- Sequential Phases: 0-10 pts (phases ordered by dependencies, each 5-15 min work)
- Explicit Non-Goals: 0-8 pts (dedicated Non-Goals section with explicit boundaries)
- Structured Format: 0-7 pts (FR codes, consistent headings, Given-When-Then criteria)
Category B: Traditional PRD Core (25 points)
- Problem Statement: 0-7 pts (quantified pain points, metrics)
- Goals & Metrics: 0-8 pts (SMART goals, P0/P1 priorities)
- User Personas: 0-5 pts (named personas with scenarios)
- Technical Specs: 0-5 pts (architecture, integrations, data models)
Category C: Implementation Clarity (30 points)
- Functional Requirements: 0-10 pts (FR codes, P0/P1/P2, acceptance criteria)
- Non-Functional Requirements: 0-5 pts (security, performance, reliability)
- Architecture: 0-10 pts (diagrams, data flow, API contracts)
- Phased Implementation: 0-5 pts (clear phases, time estimates, deliverables)
Category D: Completeness (20 points)
- Risk Assessment: 0-5 pts (3-5 risks with mitigations)
- Dependencies: 0-3 pts (external and internal)
- Examples: 0-7 pts (code snippets, API examples)
- Documentation Quality: 0-5 pts (formatting, ToC, glossary)
Step 3: Generate Score Report
Output:
## PRD Score Report: [PRD Title]
### Overall Score: XX/100 ([Grade])
Grade Scale: A+ (90-100), A (80-89), B (70-79), C (60-69), D (<60)
| Category | Score | Max |
|----------|-------|-----|
| A. AI-Specific Optimization | XX | 25 |
| B. Traditional PRD Core | XX | 25 |
| C. Implementation Clarity | XX | 30 |
| D. Completeness | XX | 20 |
### Top 3 Improvement Recommendations
1. [Highest impact fix] - +X points
2. [Second priority] - +X points
3. [Third priority] - +X points
### Verdict
[1-2 sentence summary of PRD quality and AI-readiness]
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.
- 1mo ago First seen · 118 lines · 14 tokens per session scan A 5c21295c40f6
octo-prd-score is a command published in the GitHub repository CES-Ltd/Lumi (40 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,041 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to octo-prd-score, differing in 5 lines, and is treated as a copy.
Other commands, from other repositories
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
sonarqube
Analyze SonarCloud quality issues for a specific PR.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
resolve-dependabot-prs
Triage open Dependabot PRs, return a quick risk/action summary table, then enter planning mode with an ordered rebase→merge→follow-up→resume resolution plan.
create-task-list.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.