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 skills add summarybotng/summarybot-ng --skill sfdipot-product-factorsgit clone --depth 1 https://github.com/summarybotng/summarybot-ngWrote 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/skills/summarybotng/summarybot-ng/sfdipot-product-factors)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/sfdipot-product-factors"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/sfdipot-product-factors/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/skills/summarybotng/summarybot-ng/sfdipot-product-factors"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/sfdipot-product-factors.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 | $0.00060 | $0.01906 |
| Opus 5 | $0.00030 | $0.00953 |
| Sonnet 5 | $0.00012 | $0.00381 |
| Haiku 4.5 | $0.00006 | $0.00191 |
Grade A, and why
sfdipot-product-factors 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SFDIPOT Product Factors Analysis
<default_to_action> When analyzing requirements:
- IDENTIFY document type (epic, user story, spec, architecture doc)
- DETECT domain context (ecommerce, healthcare, finance, etc.)
- ANALYZE each SFDIPOT category systematically
- GENERATE test ideas with action verbs (no "Verify" patterns)
- ASSIGN priorities (P0-P3) and automation fitness
- SURFACE clarifying questions for coverage gaps
- OUTPUT in requested format (HTML, JSON, MD, Gherkin)
Quality Gates:
- Human exploration >= 10%
- No "Verify X" test patterns
- Priority distribution: P0 (8-12%), P1 (20-30%), P2 (35-45%), P3 (20-30%) </default_to_action>
Quick Reference Card
The 7 Product Factors
| Factor | Question | Example Focus Areas |
|---|---|---|
| Structure | What IS it? | Components, code, dependencies |
| Function | What does it DO? | Features, calculations, errors |
| Data | What does it PROCESS? | Input, output, persistence |
| Interfaces | How does it CONNECT? | UI, API, integrations |
| Platform | What does it DEPEND ON? | OS, browser, hardware |
| Operations | How is it USED? | Workflows, admin, recovery |
| Time | WHEN do things happen? | Concurrency, scheduling |
When to Use This Skill
| Scenario | Priority | Output |
|---|---|---|
| New epic planning | High | Full SFDIPOT assessment + test ideas |
| Sprint requirement review | Medium | Targeted analysis + clarifying questions |
| Test strategy definition | High | Comprehensive test coverage plan |
| Risk assessment | High | Domain-weighted priority assignment |
| Coverage gap analysis | Medium | Penetrating questions + recommendations |
SFDIPOT Analysis Framework
Structure (What the product IS)
Subcategories:
- Code Integrity: Code quality, complexity, maintainability
- Hardware: Physical components, devices, peripherals
- Non-Executable Files: Config, data files, documents
- Executable Files: Binaries, scripts, libraries
- Dependencies: Third-party libraries, external services
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 · 240 lines · 60 tokens per session scan A f8cd55b13e95
sfdipot-product-factors is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,906 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
qa-domain-modeling
A way to map complex business logic using state machines, data-flow diagrams, and service-dependency diagrams. A state machine shows how an object changes state, while a data-flow diagram shows how information moves between parts of a system.
qa-req-deconstruction
A Chinese-language method for breaking vague requirements into testable inputs, actions, states, outputs, and rules. It also looks for unstated needs involving errors, limits, timing, data changes, security, and simultaneous use.
qa-scenario-tree
A method for organizing tests as a tree of normal user journeys, alternative choices, failures, business rules, and data changes. It helps connect each scenario back to the requirement it checks.
qa-requirement-review
A guide for reviewing a requirements document across completeness, clarity, consistency, testability, and feasibility. Requirements documents describe what a product or feature should do.
delivery-proof
Delivery proof and the doublecheck report. Use when the work is done and the delivery must be proven — consolidate the spec, test timeline, review verdicts, and verification checks into a doublecheckreport, and only then claim completion.
red-green-tdd
Red/green test discipline for implementation work. Use once a doublecheck spec is on record and implementation is about to start — write a test that fails for the missing behavior, run it to see it fail (red), make the change, run again to see it pass (green).