envision

A project-vision interview that records a project's purpose, user experience, module boundaries, and relationships in versioned files.

In plain words
What is it for?
Use it to explore a project's intent and structure, divide it into candidate modules, and save a versioned vision under .claude/visions/.
Why use it?
It helps establish the project's overall direction before writing detailed feature specifications.

Command

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 commands/ackeskin/contexture/envision
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 300 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 $0.00077 $0.00300
Opus 5 $0.00039 $0.00150
Sonnet 5 $0.00015 $0.00060
Haiku 4.5 $0.00008 $0.00030

Measured 2d ago against content hash 2ff0c52b0559, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

commands/envision.md · 17 lines

What it actually says

Run the envision skill for the current context.

Forms:

  • /envision — write to the reserved default slug (the repo itself is the project).
  • /envision <slug> — named slug; create v1.md if new, else evolve the active version.
  • /envision <slug> --new — explicit fresh slug; refuse if <slug> already exists in INDEX.
  • /envision <slug> --abandon — mark the active version abandoned; no new file written.

The skill runs a breadth-first interview (intent, UX, module partition, boundaries, relations, cross-cutting concerns, non-goals), refuses spec-level detail, grounds via /discover, produces a mandatory module-map diagram, and writes the versioned vision under .claude/visions/<slug>/ plus INDEX.md. Each module it names becomes a candidate slug for /spec. It does not spec, plan, or execute.

See ~/.claude/skills/envision/SKILL.md for the full procedure.

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 · 17 lines · 77 tokens per session scan A 2ff0c52b0559

Subscribe to this mod's changes

envision is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 300 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 2026-08-31.