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/datasift-ty-personal/siftstack/playbook-creatornpx skills add DataSift-Ty-Personal/SiftStack --skill playbook-creatorgit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWrote 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/datasift-ty-personal/siftstack/playbook-creator)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/playbook-creator"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/playbook-creator.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 | $0.00000 | $0.05586 |
| Opus 5 | $0.00000 | $0.02793 |
| Sonnet 5 | $0.00000 | $0.01117 |
| Haiku 4.5 | $0.00000 | $0.00559 |
Grade C, and why
playbook-creator scanned grade C with 1 finding 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 today.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**Never refuse to create.** Always produce something, even from poor input. Flag sections that need user review with a note like: `> **Needs Review:** This step was unclear in the source. Please confirm the exact action. How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playbook & SOP Creator
This skill creates professional documentation in three formats:
- SOP - step-by-step operational procedure for a specific, repeatable task. Ships as a PAIR: a human Word doc plus an agent-executable
.sop.mdtwin. - Playbook - strategic framework covering a system of processes, with mental models and decision logic.
- Step Guide - a Scribe-style click path: one screen action per step, one screenshot per step, nothing else.
All formats include process maps built with Mermaid where flow needs visualizing, screenshot capture specs for software interfaces, and are written at a 5th-grade reading level so anyone on a team can follow them.
The skill works from multiple input types: raw transcripts (meetings, training calls, screen shares), written descriptions, existing documentation, or just a topic the user wants documented. When working from transcripts, it extracts the actual workflow being demonstrated - the clicks, the decisions, the order of operations - and structures it into clean documentation.
Input Detection
Understand what the user gave you and adapt:
| Input Type | What to Do |
|---|---|
| Raw transcript (meeting notes, Fireflies, call recording) | Extract the workflow being taught. Identify the teacher vs. learner. Pull out the actual steps, decision points, tools used, and tips mentioned. Ignore small talk and tangents. |
| Topic only ("create a playbook for pulling foreclosures") | Research the topic using available tools and your knowledge. Ask clarifying questions about their specific tools and workflow. |
| Existing doc (rough notes, bullet points, old SOP) | Restructure into the proper template. Improve clarity. Add process maps and visual aids. |
| Screen share / walkthrough description | Treat like a transcript - extract the sequential actions, what was clicked, what was checked, and what decisions were made. This input usually wants a Step Guide. |
| Video recording (screen recording with narration) | The richest input: the narration carries the steps and judgment, the frames ARE the screenshots. See "Video Input" below. |
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 3.7 KB
- references/agent-sop-format.md 6.6 KB
- references/foreclosure-example.md 12 KB
- references/playbook-template.md 6.7 KB
- references/process-mapping-guide.md 10 KB
- references/screenshot-guide.md 4.2 KB
- references/sop-template.md 8.5 KB
- references/step-guide-template.md 5.6 KB
- references/voice-guide.md 4.2 KB
- scripts/build_docx.js 26 KB runs code
- scripts/build_pdf.py 18 KB runs code
- scripts/transcribe_video.py 8.0 KB runs code
- scripts/validate_sop.py 4.5 KB runs code
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.
- today Changed · -9 lines · -171 tokens per session a561449f43c3
- 4d ago First seen · 404 lines · 171 tokens per session scan C c6734938cb77
playbook-creator is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,586 tokens. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…