human-view

A command that turns a machine-oriented project plan, specification, or similar planning file into plain language for a person to review. It also shows the main goal, important decisions, possible changes in scope, and unanswered questions.

In plain words
What is it for?
Use it to review a plan by its project name or file path, optionally saving a copy in an Obsidian vault. It helps approve plans and check that earlier discussions led to the right result.
Why use it?
Planning files written for AI can be difficult for people to check. This gives you a readable version so you can spot misunderstandings before work begins.

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/human-view
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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 $0.00056 $0.00318
Opus 5 $0.00028 $0.00159
Sonnet 5 $0.00011 $0.00064
Haiku 4.5 $0.00006 $0.00032

Measured 2d ago against content hash 666ca30bcaac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commands/human-view.md · 18 lines

What it actually says

Run the human-view skill.

Forms:

  • /human-view <slug> — render the human view of the slug's active artefact (prefers plan → blueprint → spec → vision; asks if ambiguous).
  • /human-view <path> — render the human view of a specific artefact file.
  • /human-view <slug|path> --vault — also write a human copy to the Obsidian vault.

Every planning artefact is written token-optimized for the LLM. This renders the opposite: a plain-prose view of what's actually in the LLM's head — the goal in one breath, what was decided (and why it matters), an alignment check (where it narrowed/expanded/reinterpreted your ask), and the open questions — so you can approve it and catch a misalignment before it ships into /execute.

It is a faithful projection (never modifies the source, never invents or softens), library-callable by the /draft-plan and /blueprint review gates, and never auto-fires. The LLM artefact stays the source of truth.

See ~/.claude/skills/human-view/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 · 18 lines · 56 tokens per session scan A 666ca30bcaac

Subscribe to this mod's changes

human-view is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 318 once invoked, about $0.0003 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.