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 skills/stefan-jansen/claude-code-toolkit/scqa-frameworknpx skills add stefan-jansen/claude-code-toolkit --skill scqa-frameworkgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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 | $0.00019 | $0.02634 |
| Opus 5 | $0.00010 | $0.01317 |
| Sonnet 5 | $0.00004 | $0.00527 |
| Haiku 4.5 | $0.00002 | $0.00263 |
Grade A, and why
scqa-framework 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.
How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCQA Framework Skill
Foundation: McKinsey's SCQA (Situation-Complication-Question-Answer) framework, derived from Barbara Minto's pyramid principle
Core Concept: Build compelling narrative by establishing situation, introducing complication, raising question, then delivering answer.
Why This Works:
- Engages reader with familiar situation
- Creates tension with complication (problem)
- Raises question reader now wants answered
- Delivers answer with impact (reader is primed)
- Natural storytelling flow
The SCQA Structure
Four elements in sequence:
1. Situation (S)
What: The stable, uncontroversial starting point everyone agrees on
Purpose: Establish common ground with reader
Example:
"Software engineers use AI coding assistants to boost productivity."
Characteristics:
- Non-controversial (reader nods along)
- Familiar to target audience
- Sets the stage for complication
2. Complication (C)
What: The problem, change, or challenge that disrupts the situation
Purpose: Create tension and make reader care
Example:
"But generic AI agents produce unreliable code - state corruption, context loss, hallucinations. Teams abandon them after weeks of frustration."
Characteristics:
- Introduces conflict/problem
- Makes status quo untenable
- Resonates with audience pain
- Creates urgency
3. Question (Q)
What: The question reader now wants answered (often implicit)
Purpose: Focus attention on the answer you're about to provide
Example:
"How can we get AI productivity benefits without the reliability chaos?"
Characteristics:
- Natural question arising from complication
- What reader is now thinking
- Can be explicit or implicit
- Sets up your answer
4. Answer (A)
What: Your solution, recommendation, or core message
Purpose: Deliver the answer reader is now primed to receive
Example:
"CAF provides production-grade architecture that prevents AI chaos through stateless, file-based patterns proven over 6 months."
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 · 412 lines · 19 tokens per session scan A eb0c11b9f776
scqa-framework is a skill published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,634 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 skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
code-change-verification
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
prior-auth-packet-builder
Build a concise prior authorization packet from local case files and payer policy docs.
pdf-processing
Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.
document-service
This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs"…