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 sruthir28/enterprise-ai-skills --skill stakeholder-mapgit clone --depth 1 https://github.com/sruthir28/enterprise-ai-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/sruthir28/enterprise-ai-skills/stakeholder-map)<a href="https://agentmods.dev/skills/sruthir28/enterprise-ai-skills/stakeholder-map"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/stakeholder-map/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/sruthir28/enterprise-ai-skills/stakeholder-map"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/stakeholder-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.02219 |
| Opus 5 | $0.00041 | $0.01110 |
| Sonnet 5 | $0.00016 | $0.00444 |
| Haiku 4.5 | $0.00008 | $0.00222 |
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 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stakeholder Map
Most decisions don't fail because the analysis was wrong. They fail because the person who could kill it wasn't bought in, or the person who could champion it wasn't asked. This skill makes the politics visible so you can plan around them — without pretending strategy and people are separate problems.
The output is a 2x2 grid + a per-stakeholder action plan. You walk away knowing exactly who you talk to first, what you say, and who you can ignore.
Design choices
- Real names, not roles. "Head of Eng" hides the fact that this Head of Eng has been here 3 months and has political capital below the team they inherited. Use names.
- Power × Interest, not Influence × Impact. Power = can they kill the decision. Interest = do they care about the outcome. The right axes for politics, not for delivery management.
- One move per stakeholder. Not a 5-step engagement plan. The one thing you'll do this week.
- Stance is honest. Champions get celebrated, blockers get named. If everyone is "supportive," you haven't mapped honestly.
- Skip the unmappable. If you have <2 minutes of real information on a stakeholder, mark them "unknown" and make finding out their #1 action.
The grid
HIGH INTEREST LOW INTEREST
┌──────────────────────────┬──────────────────────────┐
│ │ │
HIGH │ MANAGE CLOSELY │ KEEP SATISFIED │
POWER │ (the actual deciders) │ (don't surprise them) │
│ │ │
├──────────────────────────┼──────────────────────────┤
│ │ │
LOW │ KEEP INFORMED │ MONITOR │
POWER │ (your loud allies) │ (don't waste cycles) │
│ │ │
└──────────────────────────┴──────────────────────────┘
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 First seen · 155 lines · 81 tokens per session scan A 50f1ed22e428
stakeholder-map is a skill published in the GitHub repository sruthir28/enterprise-ai-skills (139 stars, last pushed 9d ago), licensed MIT. It adds 81 tokens to every session and 2,219 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
lyrik
Security assessment of a codebase — minimal mode for runner validation.
librarian
Read-only retrieval over the daily-digest kept set. Slash-invoke with /librarian ; returns items verbatim with citations.
notes
Create and manage text notes in the workspace.
tdx-assets
Look up staff devices, assets, and locations in TeamDynamix (TDX). Given a list of names, emails, or partial identifiers, resolve each person and return the assets assigned to them with location, model, ownership type, and status. Read-only.
aggregator
Daily fetch from a fixed public allowlist; score against the user's interests file; cluster into themes; push the digest to the configured channel.
file-search
Find files and search content across directories.