Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AcKeskin/contexturenpx agentmods add skills/ackeskin/contexture/blueprintWrote 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/blueprint)<a href="https://agentmods.dev/skills/ackeskin/contexture/blueprint"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/blueprint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ackeskin/contexture/blueprint"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/blueprint.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00102 | $0.03546 |
| Opus 5.5 | $0.00041 | $0.01418 |
| Sonnet 5.5 | $0.00020 | $0.00709 |
| Haiku 4.5 | $0.00010 | $0.00355 |
Grade A, and why
blueprint 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blueprint
The concrete-blueprint organ.
A blueprint puts two things side by side so a competent engineer can see they're aligned and commit:
- What we wanted — the original intent (from the vision + spec).
- What we're building now — the mature concrete answer: classes, interfaces, dependencies, module/class relationships, build order — the actual shape, not a narrative of how it was planned.
It is optional and post-planning — reached for after /draft-plan when you want everything concretized in one place. It does not merge with /draft-plan (the plan stays the stepped plan; the blueprint is the concrete synthesis on top):
envision → spec → draft-plan → [ blueprint ] → execute (blueprint optional)
It authors (writes new diagrams + the concrete shape). It is not visualise-codemap (which renders structure from finished code — derived, post-hoc). Mermaid templates live in mermaid-templates.md.
The point is intent + mature concrete shape, aligned. It is not a process log: how the plan was arrived at is deliberately out of scope — keep a light "key decisions" note only when it's free (§4 step 3).
When to run
- User types
/blueprint [slug] [--from-code]. - User asks to "blueprint this", "show the concrete shape", "give me the classes/interfaces/deps before I build".
/draft-plan's close offers it — but the user still invokes it explicitly.- Do not auto-fire. Manual only (per
universal/skill-auto-fire.md— a blueprint is a deliberate act, not a post-plan side effect). Optional by design: small plans rarely need it.
Inputs
- Slug. From
/blueprint <slug>, or resolved like/draft-plan(default → single active → ask) when omitted. - Mode. Mode 1 (intent-driven) by default; Mode 2 (
--from-code, or auto-selected when the slug has no vision/spec). - Project root.
$CLAUDE_PROJECT_DIRif set, else cwd. - Obsidian vault root + project folder. The vault root (
<Vault>) is read from machine-local config —vaultRootin~/.claude/hook-config.json— never hardcoded (peruniversal/no-hardcoded-machine-paths.md). IfvaultRootis absent, do not guess: surface "SetvaultRootin~/.claude/hook-config.jsonto write vault artefacts." and write only the in-repo blueprint.<ProjectFolder>inference (match an existingProjects/<Name>/subfolder under<Vault>, else ask once) — the root comes from config, not a literal.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 167 lines · 102 tokens per session scan A 1def617066ed
blueprint is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 3,546 once invoked, about $0.0004 per session on Opus 5.5. 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
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
agent-go-expert
Specialist subagent: Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
agent-svelte-expert
Specialist subagent: Svelte 5 runes, SvelteKit routing, form actions, and compile-time reactivity specialist. Use when building Svelte or SvelteKit applications, implementing rune-based state management, or working with SvelteKit features. Trigger phrases: Svelte, SvelteKit, runes, $state, $derived, $effect, $props…
literature-review-planner
Structured literature review planning with systematic methodology, source evaluation, and synthesis frameworks. Use when planning academic literature reviews, research surveys, systematic reviews, or scoping reviews.