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 skills add tmchow/tmc-marketplace --skill image-sproutgit clone --depth 1 https://github.com/tmchow/tmc-marketplaceWrote 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/tmchow/tmc-marketplace/image-sprout)<a href="https://agentmods.dev/skills/tmchow/tmc-marketplace/image-sprout"><img src="https://agentmods.dev/badge/skills/tmchow/tmc-marketplace/image-sprout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tmchow/tmc-marketplace/image-sprout"><img src="https://agentmods.dev/badge/skills/tmchow/tmc-marketplace/image-sprout.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.01432 |
| Opus 5 | $0.00032 | $0.00716 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
image-sprout 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 11d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-sprout
Generate and iterate on images with consistent style and subject identity. Image Sprout turns reusable project context — reference images, derived guides, and persistent instructions — into repeatable outputs you can build on across runs.
Use this skill when:
- The user asks to generate images and wants results that stay consistent across multiple runs
- The user wants to iterate on outputs from a previous generation
- The user needs to set up or manage an image project with references or style context
- The workflow requires structured, scriptable image generation with
--jsonoutput
1. Installation
Install globally from npm:
npm install -g image-sprout
Or run without installing — prefer this in Codex sandbox environments where PATH is unreliable:
npx image-sprout help
All examples below use npx image-sprout. Substitute image-sprout directly if you have a global install.
2. OpenRouter Key Setup
Image Sprout stores its OpenRouter key on disk. Set it once per machine:
npx image-sprout config set apiKey <your-openrouter-key>
npx image-sprout config show # confirm key is set (does not reveal the raw key)
3. The Project Model
Three context layers drive every generation:
- Visual Style — consistent look and feel across outputs
- Subject Guide — consistent subject identity across outputs
- Instructions — persistent generation constraints (watermarks, framing, branding)
Two reference pools:
- Shared refs — drive both guides (default, simplest)
- Split refs — separate style and subject pools (advanced; use
--role styleor--role subjectwhen adding)
Understanding this model prevents the most common agent mistake: generating without saved context and wondering why outputs are inconsistent.
4. Core CLI Workflow
# Create a project
npx image-sprout project create <name>
# Add references (3+ recommended; more refs = better derivation)
npx image-sprout ref add --project <name> ./ref1.png ./ref2.png ./ref3.png
# Optional: persistent instructions
npx image-sprout project update <name> --instructions "Watermark bottom-right: subtle."
# Derive guides from refs
npx image-sprout project derive <name> --target both # or: style, subject
# Check readiness before generating
npx image-sprout project status <name> --json
# Generate (--count controls images per run: 1, 2, 4, 6; default is 4)
npx image-sprout project generate <name> --prompt "hero in neon rain"
npx image-sprout project generate <name> --prompt "hero in neon rain" --count 1
# Inspect results
npx image-sprout run latest --project <name> --json
# Delete a session and all its runs/images
npx image-sprout session delete --project <name> <session-id>
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.
- 11d ago First seen · 156 lines · 64 tokens per session scan A 992156aae097
image-sprout is a skill published in the GitHub repository tmchow/tmc-marketplace (22 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 1,432 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.