stakeholders

A guide for identifying the people who should approve, advise on, or be informed about a change or project. It separates decision-makers from consultants and people who are only affected or need an update.

In plain words
What is it for?
Use it to find technical owners, approvers, advisers, and affected teams for refactors, migrations, process changes, and other decisions.
Why use it?
It prevents important people from being missed without producing an unfocused list of everyone connected to the work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gleanwork/cursor-plugins/stakeholders
Any agent
npx skills add gleanwork/cursor-plugins --skill stakeholders
Clone the repo
git clone --depth 1 https://github.com/gleanwork/cursor-plugins

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,264 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.01264
Opus 5 $0.00036 $0.00632
Sonnet 5 $0.00014 $0.00253
Haiku 4.5 $0.00007 $0.00126

Measured yesterday against content hash 40db23480b9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stakeholders 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 yesterday.

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.

Origin

This is a copy

100% identical to stakeholders — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

glean/skills/stakeholders/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stakeholder Discovery

You are helping someone identify the right people to involve in a change, decision, or project.

Determine the change, project, or decision from the user's request. If it is absent or unclear, ask the user to clarify — for example: what type of change (technical, process, or both), what is the scope (single team, cross-team, company-wide), and what systems or components will be affected.

Core Principles

  • Quality over quantity: Don't list everyone tangentially related
  • Distinguish roles: Approvers vs. consultants vs. FYI recipients
  • Be skeptical: Just because someone's name appears doesn't make them a stakeholder
  • Fewer is better: A focused list is more useful than a comprehensive one

Phase 1: Understand the Change

Goal: Clarify what's being changed and why

If the change is vague, ask the user to clarify:

  • What type of change is this? (Technical change, process change, or both)
  • What's the scope? (Single team, cross-team, company-wide)
  • What systems or components will this affect?

Phase 2: Find Stakeholders

Goal: Identify technical owners, decision makers, and affected parties

  1. Start with Glean chat for a synthesized stakeholder view:

    chat "Who are the stakeholders for [change/system]? Include code owners, decision makers, and teams that depend on this."
    
  2. Gather specific details with direct searches:

    code_search "[affected system] contributors"
    search "[affected system] RFC OR architecture doc"
    employee_search "[affected system] team lead OR manager"
    
  3. Search for downstream dependencies:

    search "[affected system] integration OR dependency OR consumer"
    

Phase 3: Vet Each Stakeholder (CRITICAL)

Goal: Filter to people who genuinely need to be involved — BE SKEPTICAL

Test ✅ Include ⚠️ Caution ❌ Reject
Direct Impact Owns affected code, manages affected team, depends on affected system Works in same general area, different systems Mentioned topic once
Authority 🔴 Approver: Has explicit sign-off | 🟡 Consultant: Should be consulted | 🟢 FYI: Should know Unclear role No clear reason to involve them
Relevance Currently owns area, actively maintains system Recently changed roles — confirm still relevant Former owner, historical involvement only
Evidence Named in CODEOWNERS, documented owner, explicit dependency Mentioned in related docs — verify Just keyword matches

Read the full file on GitHub · 164 lines

Changes

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.

  1. yesterday First seen · 164 lines · 72 tokens per session scan A 40db23480b9d

Subscribe to this mod's changes

stakeholders is a skill published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 72 tokens to every session and 1,264 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to stakeholders, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens