What is image-node-render?

A workflow step that renders a selected image concept using Codex’s built-in image generation. It reads the workflow’s prompts and settings, then saves the generated images and their manifest.

Use it to render baked or text-free overlay image variants from a prepared prompt pack and update the workflow’s image files and manifest.

It provides a defined rendering step for an image workflow and records which version was produced. If rendering cannot happen, it records that the step was blocked.

image-node-render — Command by TheSmokeDev

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-render

Clone the repo

git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 860 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.00860
Opus 5	$0.00008	$0.00430
Sonnet 5	$0.00003	$0.00172
Haiku 4.5	$0.00002	$0.00086

Measured 2d ago against content hash 777d41825d81, 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-render 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.

.archon/commands/image-node-render.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Node Render

Workflow ID: $WORKFLOW_ID

Contract

Render the prompt pack using Codex built-in image generation only. This node must never use OpenAI API keys, ad hoc SDK scripts, external marketplace services, or any fallback CLI or API renderer.

Read:

$ARTIFACTS_DIR/image-node-preflight.json
$ARTIFACTS_DIR/image-node-prompt-pack.json
$ARTIFACTS_DIR/images/manifest.json
Upstream intake JSON: $intake.output

Write:

Final generated images under $ARTIFACTS_DIR/images/
Updated $ARTIFACTS_DIR/images/manifest.json
$ARTIFACTS_DIR/render-blocked.md only if rendering is blocked

Then output ONLY the render JSON described below.

Variant Selection

Read render_mode from $intake.output.render_mode.
When render_mode is baked, render each concept's baked_prompt.
When render_mode is overlay, render each concept's overlay_prompt. The overlay copy stays as HTML data in the pack. Do not bake it here. The rendered image is the text-free scene with reserved empty space.
Record which variant was rendered in the manifest and in the render JSON.

Render Rules

When $intake.output.subject_mode is placeholder and $intake.output.persona_pack is none, do not render. Write render-blocked.md and output render_status: "blocked" with blocked_reason stating the pack carries a [SUBJECT SUPPLIED AT RENDER TIME] slot and expects a downstream renderer to supply the subject references. Rendering the placeholder literally would produce garbage.
Use the built-in Codex image generation capability for each selected prompt.
Make one image generation call per concept.
Inspect each generated image for prompt fit, visible text accuracy in the baked case, empty overlay space in the overlay case, and major visual failures.
Move or copy selected final images into $ARTIFACTS_DIR/images/. Do not leave the only copy in the default Codex generated-images location.
Use stable filenames: asset-01.png, asset-02.png, and so on.
Update the manifest with saved image paths, source concept ids, the rendered variant, and any review notes.

Read the full file on GitHub · 101 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.

2d ago First seen · 101 lines · 16 tokens per session scan A 777d41825d81

Subscribe to this mod's changes

image-node-render is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 10d ago), licensed MIT. It adds 16 tokens to every session and 860 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.

Creative and media Orchestration agent-memory ai-agents desktop-agent operating-room second-brain

obsidian-connect

Bridge two unrelated domains using your vault's link graph - forces creative friction to spark new ideas.

eugeniughelbur/obsidian-second-brain · 18 tokens

creator-pipeline

Generate a multi-modal content pipeline from a person's Genius Profile. Produces content calendar, per-piece production plan across text/audio/image/video/podcast, and attestation routing. Composes with existing modality commands + ACOS pipeline where available.

frankxai/Starlight-Intelligence-System · 51 tokens

content-systemize

Convert a content pillar into reusable production templates — title formulas, outline skeletons, voice-cloned intro/outro, modality-specific prompt templates (Suno, Nano Banana, Veo). Enables non-genius execution of a pillar's content stream.

frankxai/Starlight-Intelligence-System · 53 tokens

sip-attest-audio

Attest an audio artifact (music track, voice-over, podcast, soundscape). Generates SIP attestation embedded in ID3 tags + sidecar .sip.json. Refuses decorative use. v7.5+ — scaffold present, full implementation pending.

frankxai/Starlight-Intelligence-System · 57 tokens

arcanea-canon

Vertical-tier command for Arcanea. Manage, extend, or pin Arcanea canon — Guardians, Vel'Tara archetypes, Hz grounding, realm/essence vocabulary. Every canon operation emits "Built on SIP" attestation with CC-BY-NC license pinning. Sovereign to Arcanea BV.

frankxai/Starlight-Intelligence-System · 67 tokens

nano-banana

Generate or edit images using Google's Gemini Image model.

mycelium-hq/ai-brain-starter · 9 tokens