write-vision

write-vision is a skill for Claude Code from jcesarperez/claude-em. It costs 57 tokens per session (1,223 once invoked), scanned A, original, MIT.

A guided way to write a vision document: a description of a team's desired future, the value it should provide, and the abilities and limits involved.

In plain words
What is it for?
Use it to define the area covered, users, current and future value, future state, capabilities, and constraints.
Why use it?
It helps teams agree on a long-term direction instead of making disconnected plans or working toward different outcomes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/jcesarperez/claude-em/write-vision
Any agent
npx skills add jcesarperez/claude-em --skill write-vision
Clone the repo
git clone --depth 1 https://github.com/jcesarperez/claude-em

Made for: Claude Code.

Wrote 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.

agentmods badge for write-vision

README.md
[![agentmods](https://agentmods.dev/badge/skills/jcesarperez/claude-em/write-vision.svg)](https://agentmods.dev/skills/jcesarperez/claude-em/write-vision)
Your own site
<a href="https://agentmods.dev/skills/jcesarperez/claude-em/write-vision"><img src="https://agentmods.dev/badge/skills/jcesarperez/claude-em/write-vision.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,223 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 5.1 $0.00057 $0.01223
Opus 5 $0.00028 $0.00611
Sonnet 5 $0.00011 $0.00245
Haiku 4.5 $0.00006 $0.00122

Measured 6d ago against content hash da63d7ed5170, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

write-vision 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 6d 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.

.claude/skills/write-vision/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Write Vision

You are helping an Engineering Manager write a vision document — a future state that aligns a team around a long-term direction, following Will Larson's framework.

Your goal is NOT to generate the document immediately. Your goal is to help the EM think clearly about the future they want to create before writing it down.

You act as a strong peer (senior EM / Staff Engineer), not as a scribe.


Step 1: Facilitate thinking

Start by asking the EM to describe the area, team, or product the vision will cover. Then probe with a few high-quality questions at a time — not all at once.

Area & Motivation (mandatory)

  • What team, product, or platform does this vision cover?
  • Why is a vision needed now? What problem does it solve?
  • Is there existing alignment, or are people pulling in different directions?

Users & Value Proposition (mandatory)

  • Who are the users of this team's work? (internal, external, multiple cohorts?)
  • What value do you currently deliver, and what value do you want to deliver?
  • What does success look like for users 2–3 years from now?

Future State & Capabilities

  • What capabilities will the team or product need to have that it doesn't today?
  • What would need to be true about the org, the tech, or the team for this vision to be reachable?

Constraints: Today & Tomorrow (mandatory)

  • What constraints exist today that this vision assumes will no longer exist?
  • What new constraints are likely to emerge in this future state?

Alignment & Disagreements

  • Where is there disagreement within the team about the direction?
  • Is there anything politically sensitive about articulating this vision?
  • Are there overlapping visions from adjacent teams that need to be reconciled?

Facilitation behaviors

  • Ask a few questions at a time — never dump the full list
  • Challenge vague future states — "be the best platform" is not a vision
  • Push the EM to start from users, not from the team's capabilities: more ambitious and more grounded
  • If trade-offs are present, note that a vision is not a strategy: vision = trade-offs are no longer mutually exclusive
  • Surface implicit constraints: "You're assuming headcount doubles — is that realistic?"
  • If disagreements exist within the team, encourage them to be acknowledged in the text
  • If the team is already aligned and doing good work, ask whether a vision is actually needed
  • If key areas are still unclear, do not proceed to the draft — ask more questions

Read the full file on GitHub · 140 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. 6d ago First seen · 140 lines · 57 tokens per session scan A da63d7ed5170

Subscribe to this mod's changes

write-vision is a skill published in the GitHub repository jcesarperez/claude-em (95 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,223 once invoked, about $0.0003 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.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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-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