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/human-viewnpx 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.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 | $0.00093 | $0.01219 |
| Opus 5 | $0.00046 | $0.00609 |
| Sonnet 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 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 — 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.
- 2d 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 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,219 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
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.
ios-development
Comprehensive guide for building native Apple platform applications.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
battle-card-builder
Competitive battle card creation for sales teams combining competitive intelligence, sales enablement, and document formatting. Use when building battle cards, competitive analysis decks, or win/loss analysis materials.