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 agentmods add skills/veigap/talksmith/generate-imagenpx skills add veigap/talksmith --skill generate-imagegit clone --depth 1 https://github.com/veigap/talksmithWrote 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/veigap/talksmith/generate-image)<a href="https://agentmods.dev/skills/veigap/talksmith/generate-image"><img src="https://agentmods.dev/badge/skills/veigap/talksmith/generate-image.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.01126 |
| Opus 5 | $0.00045 | $0.00563 |
| Sonnet 5 | $0.00018 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
talksmith:generate-image 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 3d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
talksmith:generate-image — one prompt → one image (tool-agnostic)
The generation backend the image-illustrator dispatches once per <slide_id>.json args file (from talksmith:polish-images prepare-render-args). Its contract is deliberately backend-agnostic: the prompt is already fully composed (subject + palette + aspect + no-text overlay), so this skill's only job is to route it to an available image generator and save the result.
This is guidance, not a deterministic script. Image generation depends on a capability the session provides — there is no bundled model. This skill tells the dispatched subagent how to find and use whatever is available, and what to do when nothing is.
Inputs (from the args file)
| Field | Meaning |
|---|---|
prompt |
The fully-resolved generation prompt. Send it verbatim — do not re-expand, re-summarize, or add to it. The palette, aspect, and no-text constraints are already in it. |
aspect |
portrait (the aside column is a tall full-bleed strip → target ~2:3, e.g. 832×1248). landscape / square are accepted for completeness but the aside pass always passes portrait. |
output_path |
Absolute path to write the PNG to (e.g. talks/<Talk>/images/<slide-id>-<n>-aside.png). |
prompt_file |
The .imgprompt sidecar (original description + enriched prompt), for reference only. |
output_path_rel / prompt_file_rel / talk_rel |
Optional Talk-portable path twins (images/<name> + the Talk dir relative to repo_root). Prefer these when present: write to <your repo_root>/<talk_rel>/<output_path_rel> so the file lands correctly even when this worker runs in a different mount than the session that built the args. Fall back to the absolute output_path only when the twins are absent. |
Procedure
- Find an image-generation capability, in this order — stop at the first that exists:
- An MCP image-generation tool connected to the session. Discover it with
ToolSearch(queries likegenerate image,text to image,image generation); a matching tool typically takes a prompt/size and returns image bytes or a file/URL. - The host's native image generation, if the running model/agent exposes one.
- An MCP image-generation tool connected to the session. Discover it with
- Generate with the
promptverbatim, requesting theaspectdimensions (portrait ~2:3). Request PNG if the backend lets you choose format. - Save to
output_path. If the backend returns a URL or a temp file, fetch/copy the bytes tooutput_path(create parentimages/if needed). If it returns base64, decode and write. The file atoutput_pathmust be a real raster image — themd-to-deckPPTX prerequisite loads it via PIL, so a broken/empty file fails the later build. - Report
generated: <output_path>back to the image-illustrator.
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.
- 3d ago First seen · 41 lines · 90 tokens per session scan A 984acbc4d491
talksmith:generate-image is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 1,126 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…