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 stefanoskarakasis/Product-Marketing-Skills --skill stakeholder-mapsgit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote 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/stefanoskarakasis/product-marketing-skills/stakeholder-maps)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/stakeholder-maps"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/stakeholder-maps/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/stefanoskarakasis/product-marketing-skills/stakeholder-maps"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/stakeholder-maps.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 | $0.00060 | $0.03714 |
| Opus 5.5 | $0.00024 | $0.01486 |
| Sonnet 5.5 | $0.00012 | $0.00743 |
| Haiku 4.5 | $0.00006 | $0.00371 |
Grade A, and why
stakeholder-maps 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 11d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stakeholder-Maps — Skill
How This Works
Stakeholder maps built in a vacuum are a waste of time. This skill builds a map anchored to political reality: who has power, who's a hidden champion, who's a silent blocker, and what to do before you're in the room.
The skill runs in 7 steps:
Step 0 — Load brain context (ICP, positioning, GTM motion) and guardrails from /context/meta-patterns.md if it exists (e.g., "product launches without Sales Manage Closely engagement fail 80% of the time" — an example pattern shape, not a claim this skill has already observed).
Step 1 — Intake: Initiative description, success definition, timeline, and current champions/blockers.
Step 2 — Inversion: Who could sink this from inside? (If you can't name them, the map is assumed, not validated.)
Step 3 — Classification: Place each stakeholder on Power × Interest grid; assign political role (Champion, Blocker, Frozen, Gatekeeper, Performer, Floating Voter).
Step 4 — Conflict mapping: Identify stakeholder conflicts; define second-order risks and resolution owners.
Step 5 — Silent blocker scan: Which functions/roles aren't in the room but should be?
Step 6 — Output: HTML widget (grid + comms plan + conflict map + confidence assessment) + markdown diagnostic + Sprint Cards.
Step 7 — Learning Close: log the session to /context/skill-sessions.md.
Trigger
- When: Building a political stakeholder map for an initiative — who can kill it, who champions it, and what to say to each person.
- Not for: Campaign messaging → use
gaccs-briefafter this skill. Risk analysis → usepre-mortembefore this skill. GTM channel design → usego-to-market-strategy. - Example prompts:
- "Who are the stakeholders for this launch?"
- "Map the politics on this initiative"
- "Who could block this internally?"
- "Build a stakeholder map"
Inputs
- Args: Initiative description, success definition, timeline, current champions/blockers. Free format — Step 1 intake fills gaps conversationally.
- Defaults: If brain context is unavailable, this skill still runs — brain sharpens which stakeholders matter and what power they hold, but is not a hard blocker the way it is for
go-to-market-strategy. - Context keys:
/foundation/brain.md— optional but recommended. Sections 2 (ICP), 3 (Alternatives & Positioning), 8 (Execution: stakeholders, approvals)./context/skill-sessions.md— optional; check for a recentgtm-motionssession to ground stakeholder power in the actual motion chosen.gtm-motionsdeliberately never writes its output to the brain (motion choice is initiative-specific, not a durable fact), so this is a session-log lookup, not a brain section./context/meta-patterns.md— optional; recurring patterns the user has logged from prior stakeholder mapping sessions.
- Brain contract: Reads Sections 2, 3, 8. Writes: none — this skill does not write to
/foundation/brain.md; it may propose new Section 8stakeholdersorapprovalsentries, written only byproduct-marketing-contextafter the user confirms. - Personal context: if
/foundation/me.mdexists, read it for format and detail only (see the personal context rule inSKILL-SPEC.md).
What ships with it
1 file 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.
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.
- 11d ago Changed · +3 lines · -14 tokens per session 0964d3864c85
- 19d ago Changed · +1 lines 81fd80d6eee5
- 24d ago Changed · +13 lines f496ec3e3637
- 1mo ago Changed · +2 lines 24d09f40f5ef
- 1mo ago Changed · +2 lines ad5dfaa3ffa8
- 2mo ago First seen · 315 lines · 74 tokens per session scan A 2643e479acb6
stakeholder-maps is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 3,714 once invoked, about $0.0002 per session on Opus 5.5. 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
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
sprint-plan
Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.
review-resume
Comprehensive PM resume review and tailoring against 10 best practices including XYZ+S formula, keyword optimization, job-specific tailoring, and structure. Use when reviewing a PM resume, preparing for job applications, or improving resume impact.
job-stories
Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria. Use when writing job stories, creating JTBD-style backlog items, or expressing user situations and motivations.
wwas
Create product backlog items in Why-What-Acceptance format — independent, valuable, testable items with strategic context. Use when writing structured backlog items, breaking features into work items, or using the WWA format.
brainstorm-ideas-existing
Brainstorm product ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints. Use when generating new feature ideas, brainstorming solutions for an identified opportunity, or ideating with a product trio.