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 agentmods add skills/ackeskin/contexture/envisionnpx skills add AcKeskin/contexture --skill envisiongit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/envision)<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>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 | $0.00091 | $0.03387 |
| Opus 5 | $0.00046 | $0.01693 |
| Sonnet 5 | $0.00018 | $0.00677 |
| Haiku 4.5 | $0.00009 | $0.00339 |
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.
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
/specterritory. - The idea is still half-formed or blurry — run
/brainstormfirst 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 slugdefault. 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
- Project root.
$CLAUDE_PROJECT_DIRif set, else cwd. - Visions tree.
<root>/.claude/visions/. Created lazily. - Existing INDEX.
<root>/.claude/visions/INDEX.md. Parsed to decide create-vs-evolve. - Active version file (evolve flow only). Path:
<root>/.claude/visions/<slug>/v<M>.mdwhere M = active per INDEX. - Grounded context. Invoked via
skills/discover/SKILL.mdafter the interview body is populated.
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.
- 2d ago First seen · 265 lines · 91 tokens per session scan A 3a508142cbaa
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.
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.
event-planner
Event planning with timelines, budgets, vendor coordination, logistics checklists, and post-event evaluation. Use when organizing conferences, workshops, galas, or corporate events.
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.
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.
agent-teams
Team composition knowledge for Claude Code Agent Teams - when to suggest teams, optimal sizing, spawn prompt patterns.
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".