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 stakeholder-mapgit 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/stakeholder-map)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/stakeholder-map"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/stakeholder-map.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 5.1 | $0.00003 | $0.01258 |
| Opus 5 | $0.00002 | $0.00629 |
| Sonnet 5 | $0.00001 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
stakeholder-map 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A stalled decision usually isn't a logic problem; it's a stakeholder problem. Each person around the table is responding to a different set of incentives, and they often disagree about something other than what they say they disagree about. This skill maps that landscape so the PM can see where the real fault line runs and which two or three conversations would actually unblock the situation.
It does NOT script what to say. It does not produce talking points, framing language, or "how to convince X" tactics. Naming a person's incentive honestly is useful diagnosis; scripting how to leverage it is manipulation, and that violates both the brand and the craft. The PM understands the room; the PM walks into the room as themselves.
Procedure
- Read the decision and the stakeholder list. If a stakeholder is listed by role only and the dynamic depends on the specific person, note that the map will be coarse and the PM should refine it with what they know.
- For each stakeholder, record their stated position in one line — what they are publicly arguing for or against on this decision. Use the words they (likely) use, not your reframing.
- For each stakeholder, infer their likely underlying interest — the incentive structure they are responding to. Frame it as a role-level incentive ("Engineering lead is on the hook for the platform's reliability quarter; new surface area costs them"), not a personal attack. If the PM has named specifics about a person, those can sharpen the interest; if not, stay at the role level.
- Identify the real fault line — the underlying dimension along which the room actually divides. Often this is not the surface argument. Common patterns: it looks like a build-vs-buy argument and is actually a control argument; it looks like a timing argument and is actually a trust argument. State the fault line plainly.
- Identify the alignment map: who is genuinely aligned with whom on the real fault line (which is sometimes a different grouping than the surface). Note any stakeholders whose stated position and underlying interest diverge — they are arguing for X but their incentive points toward Y. That gap is often where the unblock lies.
- Identify the minimum unblock set — the two or three conversations that, if held well, would move the situation. Each conversation framed as: who, what to surface (the interest, the gap, the real fault line — not a tactic), and what a good outcome of that conversation looks like.
- Emit the output contract. Do not script what to say in any conversation.
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 · 112 lines · 3 tokens per session scan A ed8c22b7d203
stakeholder-map 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 1,258 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.