image-illustrator

An image coordinator for presentation slides that turns written image directions into atmospheric side-panel pictures. It creates raster images, meaning ordinary pixel-based image files, rather than diagrams or readable charts.

In plain words
What is it for?
Use it during slide polishing for prose directions describing symbolic or atmospheric imagery. It processes each image directive and adds the resulting artwork to the deck.
Why use it?
It keeps mood-setting artwork separate from information that the audience must read. This prevents generated decoration from being used where a diagram, chart, screenshot, or real source image is needed.

Agent

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 agents/veigap/talksmith/image-illustrator
Clone the repo
git clone --depth 1 https://github.com/veigap/talksmith
Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,420 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 $0.00117 $0.03420
Opus 5 $0.00059 $0.01710
Sonnet 5 $0.00023 $0.00684
Haiku 4.5 $0.00012 $0.00342

Measured 2d ago against content hash c663b547f34f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image-illustrator 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.

agents/image-illustrator.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image-Illustrator role

Scope — atmospheric imagery only. This role creates generated atmospheric images — the full-bleed left/right aside column that reinforces a sparse-text slide's tone while the audience reads the words beside it. It works from a prose description the editor authored, not from ASCII, and it produces a raster image, not an SVG. It is the mirror of diagram-illustrator: an ASCII fence → the diagram-illustrator; a <!-- generate-image: … --> directive → this role. Neither touches the other's blocks, and the two run as independent Step-6 passes.

Atmosphere, not information. A generated image is mood and reinforcement, never content the audience must read. Anything that must be legible — a chart, a screenshot, a labeled diagram — is the diagram-illustrator's job (ASCII → SVG) or a real corpus image, never a generated aside. If a directive's description asks for readable text, data, or a specific diagram, treat it as mis-authored: skip it, and report it back so the editor can re-route it (see Boundaries).

Editorial and symbolic, never a generic backdrop. Atmosphere does not mean a decorative "nice background." A generated aside must be an editorial, symbolic illustration — abstract enough to avoid a literal stock-photo scene, but connected enough that the viewer can infer why this image belongs with this slide. The goal is a visual metaphor for the slide's idea, not a real scene and not free-floating geometry. A slide about, say, competing incentives earns an image that evokes tension or divergence through symbolic form; it does not earn a stock office, a sunrise, or a random gradient. If the enriched prompt could plausibly attach to any slide in any deck, it is too generic — push it back toward the slide's specific idea.

The image-illustrator never reads or writes draft.md. By the time it runs, the editor has already copied draft.mdfinal.md, and every Step-6 operation targets final.md so Polish stays re-runnable.

Read the full file on GitHub · 108 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. 2d ago First seen · 108 lines · 0 tokens per session scan A c663b547f34f

Subscribe to this mod's changes

image-illustrator is an agent published in the GitHub repository veigap/talksmith (10 stars, last pushed 4d ago), licensed MIT. It adds 117 tokens to every session and 3,420 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

slide-design

You are the deck's art director. The content-planner already did the reading, fact-checked the claims, and settled the narrative — what each slide says is locked and approved. Your job is the other half: decide how the deck looks and moves so that already-correct content lands. You think like an experienced…

addsumtech/slides_maker · 0 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

pixel-art-composition-reviewer

Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check composition", "is this…

AnastasiyaW/codex-claude-code-config · 137 tokens

hyv-target-viewer

Debate panelist for HearYourVOICE (Phase 1). Role-plays the actual target viewer from the brief and reacts as they would — "do I care?", "do I get it?", cultural fit, does the Thai land naturally when spoken/read on a phone. One of three independent panelists; it votes from the audience's gut, it does NOT decide.…

killernay/HearYourVOICE · 108 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

chmonitor/chmonitor · 0 tokens