image-node-intake

image-node-intake is a command for coding agents from TheSmokeDev/taskchad-os. It costs 12 tokens per session (1,208 once invoked), scanned A, original, MIT.

A workflow command that reads a visual brief and converts it into a compact intake JSON object. JSON is a structured text format used to pass settings between workflow steps.

In plain words
What is it for?
Use it to capture settings such as image category, aspect ratio, render mode, image count, design references, and subject handling.
Why use it?
It makes the brief consistent and machine-readable before template selection, prompt writing, or image rendering 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/thesmokedev/taskchad-os/image-node-intake
Clone the repo
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

Wrote 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.

agentmods badge for image-node-intake

README.md
[![agentmods](https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/image-node-intake.svg)](https://agentmods.dev/commands/thesmokedev/taskchad-os/image-node-intake)
Your own site
<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/image-node-intake"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/image-node-intake.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,208 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 $0.00012 $0.01208
Opus 5 $0.00006 $0.00604
Sonnet 5 $0.00002 $0.00242
Haiku 4.5 $0.00001 $0.00121

Measured 4d ago against content hash 131c54a506c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image-node-intake 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 4d 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.

.archon/commands/image-node-intake.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Node Intake

Workflow ID: $WORKFLOW_ID

Contract

You are the intake node for a marketplace-public Archon workflow. Parse the operator's visual brief into a compact, deterministic brief JSON. Do not choose a template here. Do not render images. Do not call OpenAI APIs. Do not embed absolute local run paths or private system names in the output.

Read:

  • Original request: $ARGUMENTS
  • Preflight artifact: $ARTIFACTS_DIR/image-node-preflight.json

Write:

  • $ARTIFACTS_DIR/image-node-brief.json

Then output ONLY the same JSON object.

Inline Controls

Respect explicit inline controls when present in the brief:

  • category= a library category name or the word auto (default auto)
  • render_mode= baked or overlay (default overlay)
  • aspect= a ratio or size
  • count= a number, never above 8
  • render= true or false
  • design_file= an optional relative brand design reference, or none
  • persona_pack= an optional relative subject reference, or none
  • subject_mode= generic or placeholder (default generic). In placeholder mode the prompt pack must NOT invent a subject: every prompt carries a literal [SUBJECT SUPPLIED AT RENDER TIME] slot for a downstream renderer to fill with its own reference-locked subject.
  • exact_text="..." verbatim copy for the baked variant

Render Mode

  • render_mode selects which variant the render node will generate later. It does NOT restrict the prompt pack. The prompt pack always emits both a baked variant and an overlay variant so the two can be compared.
  • Default render_mode is overlay, the house discipline of a text-free scene plus a separate copy block for HTML overlay. Do not force it. If the operator passes render_mode=baked, keep baked.
  • render_requested comes from the preflight JSON unless the brief clearly sets render=.

Category Hint

Do not lock a template. Emit category_hint as one of the library categories below, or auto when the brief does not clearly imply one. The select node does the authoritative, skill-backed template choice.

Read the full file on GitHub · 131 lines

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. 4d ago First seen · 131 lines · 12 tokens per session scan A 131c54a506c3

Subscribe to this mod's changes

image-node-intake is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 12d ago), licensed MIT. It adds 12 tokens to every session and 1,208 once invoked, about $0.0001 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 2026-08-30.