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 skills add AcKeskin/contexture --skill human-viewgit 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/human-view)<a href="https://agentmods.dev/skills/ackeskin/contexture/human-view"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/human-view/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/human-view"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/human-view.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 | $0.00093 | $0.01219 |
| Opus 5.5 | $0.00037 | $0.00488 |
| Sonnet 5.5 | $0.00019 | $0.00244 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
human-view 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
human-view
The human-projection organ. Every planning artefact — spec, draft-plan, blueprint, vision — is written token-optimized for the LLM. At approval time the engineer needs the opposite: a human-readable view of what's actually in the LLM's head, to answer "is this aligned with what I wanted, and were the discussions pointing at the right thing?"
This is the README's two-doc-tracks principle (humans vs agents) — already applied to the shipped corpus (AGENTS.md/Copilot projections) — extended to the working artefacts. The LLM artefacts stay terse; this renders a human face on demand, the same projection pattern as deliver and the AGENTS.md projector. It does not bloat the source.
When to run
- Library call (primary): the
draft-planandblueprintreview gates invoke it to render the human view of the drafted artefact before the accept/edit/reject prompt.specandenvisionmay call it too. /human-view <artefact-path | slug>(thin command): render the human view of an existing artefact on demand — "show me the plan in human terms", "let me see what we actually decided".- Mode A — never auto-fires; never writes the source artefact (read + project only).
What it produces
A plain-prose approval view of the artefact, structured for a human scanning to approve, not an LLM executing:
- The goal, in one breath — what this is trying to achieve, in plain language (from the artefact's intent/problem/goal).
- What we decided — the concrete, load-bearing decisions as short prose bullets (the steps/shape/requirements that matter), not the token-compressed body. Translate IDs, refs, and shorthand into readable statements.
- Alignment check — "does this match what you asked for?" — surface where the artefact narrowed, expanded, or reinterpreted the original ask, so a misalignment is visible before approval.
- Open questions / risks — what's still unresolved or assumed, in plain terms.
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 · 62 lines · 93 tokens per session scan A 71d6988409dc
human-view is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 1,219 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.