envision

envision is a skill for Claude Code from AcKeskin/contexture. It costs 91 tokens per session (3,387 once invoked), scanned A, original, MIT.

An interview-led document for shaping a new project at a high level. It records the project's purpose, users, major modules, boundaries, relationships, and non-goals before detailed specifications are written.

In plain words
What is it for?
Defining a greenfield project's direction, dividing it into modules, setting ownership boundaries, and recording what is out of scope.
Why use it?
It helps settle the overall shape of a project before the team spends time designing individual features.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: names the AskUserQuestion tool.

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/ackeskin/contexture/envision
Any agent
npx skills add AcKeskin/contexture --skill envision
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 envision

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/envision.svg)](https://agentmods.dev/skills/ackeskin/contexture/envision)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/envision"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/envision.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,387 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 $0.00091 $0.03387
Opus 5 $0.00046 $0.01693
Sonnet 5 $0.00018 $0.00677
Haiku 4.5 $0.00009 $0.00339

Measured 2d ago against content hash 3a508142cbaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

envision 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 2d 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.

skills/envision/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

envision

Greenfield project shaping. Captures what a project is, who uses it and how, what modules it breaks into, what each module owns and does not own, how they relate, and what is explicitly out of scope — into a single versioned vision file. Upstream of /spec; every module the vision names becomes a candidate slug for its own /spec run.

The discipline is breadth-over-depth. The skill refuses to let the interview drift into spec-level detail — when the user starts describing functions, files, or data shapes, the skill redirects.

When to run

  • User types /envision (no args) or /envision <slug>.
  • User asks to sketch / draw / partition / shape / map a new project at the top level.
  • Manual evolution: user types /envision <slug> for an existing slug → evolve flow on the deltas.

Do not auto-fire. Do not invoke as part of any other skill's chain. /envision is user-invoked only.

Do not run when:

  • The user is asking about one piece of an existing system. That's /spec territory.
  • The idea is still half-formed or blurry — run /brainstorm first to shape it (name, description, edges, end-goal), then come back to /envision.
  • The project already has clear requirements and the user just wants to build. Skip straight to /spec.
  • The conversation is about a one-line fix, a refactor, or any task with no architecture decision attached.

Forms

  • /envision — write to reserved slug default. For the case where the repo is the project.
  • /envision <slug> — named slug. Create if new in INDEX, evolve if existing.
  • /envision <slug> --new — explicit fresh slug. Refuse if slug exists.
  • /envision <slug> --abandon — mark active version abandoned.

<slug> must match ^[a-z0-9][a-z0-9-]*$.

Inputs

  1. Project root. $CLAUDE_PROJECT_DIR if set, else cwd.
  2. Visions tree. <root>/.claude/visions/. Created lazily.
  3. Existing INDEX. <root>/.claude/visions/INDEX.md. Parsed to decide create-vs-evolve.
  4. Active version file (evolve flow only). Path: <root>/.claude/visions/<slug>/v<M>.md where M = active per INDEX.
  5. Grounded context. Invoked via skills/discover/SKILL.md after the interview body is populated.

Read the full file on GitHub · 265 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. 2d ago First seen · 265 lines · 91 tokens per session scan A 3a508142cbaa

Subscribe to this mod's changes

envision is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 3,387 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

customer-success

Support workflows, ticketing systems (Zendesk, Intercom), knowledge base design, chatbot design, and metrics (CSAT, NPS). Use when building support infrastructure, designing help centers, or optimizing customer experience.

travisjneuman/.claude · 47 tokens

event-planner

Event planning with timelines, budgets, vendor coordination, logistics checklists, and post-event evaluation. Use when organizing conferences, workshops, galas, or corporate events.

travisjneuman/.claude · 37 tokens

hr-talent

HR and talent management expertise for talent acquisition, performance management, compensation strategy, organizational design, culture building, succession planning, and D&I programs. Use when hiring, managing performance, designing organizations, or building culture.

travisjneuman/.claude · 47 tokens

innovation

Innovation management expertise for innovation frameworks (Design Thinking, Stage-Gate), ideation processes, innovation portfolio management, venture capital, open innovation, and IP strategy. Use when driving innovation, managing R&D portfolios, or building innovation programs.

travisjneuman/.claude · 49 tokens

agent-teams

Team composition knowledge for Claude Code Agent Teams - when to suggest teams, optimal sizing, spawn prompt patterns.

travisjneuman/.claude · 24 tokens

ship-roadmap

Found or continue a roadmap autopilot one stage per invocation. Default: human merge. --fullauto is invocation-scoped and uses the transient wrapper only after a fresh audit. Triggers: "ship-roadmap", "ship the roadmap", "autopilot this project".

gtrabanco/agentic-workflow · 59 tokens