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/generous-corp/pulp/decidenpx skills add Generous-Corp/pulp --skill decidegit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/decide)<a href="https://agentmods.dev/skills/generous-corp/pulp/decide"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/decide.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 | $0.00064 | $0.01108 |
| Opus 5 | $0.00032 | $0.00554 |
| Sonnet 5 | $0.00013 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
decide 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
decide — put a real choice in front of the user
Work stops on decisions. The default failure is to bury the decision at the bottom of a long status message as "let me know how you want to proceed", which makes the user reconstruct the options, the tradeoffs, and what you recommend — work you already did and then threw away.
This skill is the opposite: surface the decision as selectable options, say what you would do, and be honest about what each choice costs.
When to use it
- A product or design decision that is genuinely the user's (naming, scope, whether a capability ships)
- An approval gate (signing, publishing, anything outward-facing or hard to reverse)
- Two defensible implementations where the tradeoff is taste or risk appetite
- A destructive or irreversible step (deleting a release, rewriting history, changing branch protection)
- You are about to write "which would you prefer?" in prose
When NOT to use it
- The answer is discoverable from the code, the repo, or a doc — go find it
- One option is clearly correct and the others are strawmen — just do it and say what you did
- The decision is reversible and cheap — make the call, state the assumption
- You are asking permission for ordinary work the user already asked for
A question you could have answered yourself costs more than a wrong default.
How to ask (Claude Code)
Use the AskUserQuestion tool. The shape that works:
- Lead with the recommendation. Put it first in the options list and mark
it
(Recommended)in the label. Do not hide it in a description. - Every option gets a real tradeoff. The
descriptionsays what happens if chosen, including the cost. An option with no downside is usually a strawman, and listing it makes the whole set less trustworthy. - Keep labels short (1–5 words) — they are chips, not sentences.
header≤ 12 chars — it renders as a tag.- Batch related decisions into one call (up to 4 questions) so the user answers a set rather than being interrupted repeatedly.
- Use
multiSelect: truewhen the choices genuinely compose, e.g. "which of these should ship in the next build". - Use
previewwhen the user is choosing between concrete artifacts — layouts, copy, code shapes, diagrams. It renders side-by-side monospace, so an ASCII mockup or a short snippet lands far better than a description of one. Single-select only.
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 First seen · 105 lines · 64 tokens per session scan A 3f1ecfb9afc9
decide is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 1,108 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…