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 Waddling-Penguin/mogkit --skill tradeoff-framegit clone --depth 1 https://github.com/Waddling-Penguin/mogkitWrote 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/waddling-penguin/mogkit/tradeoff-frame)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/tradeoff-frame"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/tradeoff-frame/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/waddling-penguin/mogkit/tradeoff-frame"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/tradeoff-frame.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 | $0.00003 | $0.01219 |
| Opus 5 | $0.00002 | $0.00609 |
| Sonnet 5 | $0.00001 | $0.00244 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
tradeoff-frame 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Most contested product decisions are stuck not because the answer is hard but because the disagreement is on a different axis than the conversation. People argue about option A vs option B when the real disagreement is about what we're optimizing for. This skill exposes the structure so the humans can actually decide.
It frames the decision: the axes that matter, what each option wins and loses on each axis, whether the decision is reversible, and the evidence that would genuinely change a reasonable person's mind.
It does NOT pick the answer. It does not weight the axes. It does not say "Option B is best." Picking the answer is the human's call — and often the choice is properly the call of someone not the PM (an exec, a customer, the market). Outsourcing the choice to a tool removes the act of judgment that the role exists to perform.
Procedure
- Read the decision and the candidate options. If the options listed are not genuinely distinct (one is a strict superset of another, or two are the same thing in different words), say so and ask the PM to clarify before continuing.
- Identify the real axes of disagreement — the underlying dimensions on which the options differ in ways that matter. Common axes include speed to ship, scope of bet, reversibility, organizational cost, customer surface area, technical debt, optionality. Pick the axes specific to this decision; do not list every possible axis.
- For each option, write its optimize / sacrifice profile across the axes. Be specific. "Optimizes for speed" is too vague; "Ships in two weeks but locks the data model in a way we'd need to migrate to change" is the bar.
- Classify the decision's reversibility. One-way door (hard to undo — data model changes, public commitments, hires, deprecations of paying customers' surfaces) or two-way door (reversible at low cost). If different options have different reversibility, call that out — sometimes the right move is the two-way-door option because it's reversible.
- Identify the decisive evidence — what would a reasonable proponent of one option accept as a reason to change their mind? If the answer is "nothing would," the disagreement is values-based, not evidence-based, and that itself is the most important finding.
- Optionally, identify any hidden axis — a real consideration nobody is naming in the conversation that is actually doing a lot of the work. Common ones: career incentive, sunk-cost loyalty to a prior decision, blast radius if it goes wrong.
- Emit the output contract. Do not recommend an option.
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.
- 9d ago First seen · 109 lines · 3 tokens per session scan A 389950fd3c9f
tradeoff-frame is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 3 tokens to every session and 1,219 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.