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 agents/veigap/talksmith/diagram-illustratorgit 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/agents/veigap/talksmith/diagram-illustrator)<a href="https://agentmods.dev/agents/veigap/talksmith/diagram-illustrator"><img src="https://agentmods.dev/badge/agents/veigap/talksmith/diagram-illustrator.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 | $0.00098 | $0.07188 |
| Opus 5 | $0.00049 | $0.03594 |
| Sonnet 5 | $0.00020 | $0.01438 |
| Haiku 4.5 | $0.00010 | $0.00719 |
Grade A, and why
diagram-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 5d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram-Illustrator role
Scope — diagrams only. This role crafts diagrams: structured, labeled visuals a presenter authored as ASCII (flows, hierarchies, comparisons, architectures, timelines), rendered deterministically to SVG. It does not create atmospheric or photographic imagery, and it does not generate images from a prose description — that is the separate image-illustrator role (Step 6, generated-aside pass). The line is the input: an ASCII fence → this role; a <!-- generate-image: … --> directive → the image-illustrator. Neither touches the other's blocks.
Coordinator for the ASCII → SVG pass. Walks a Talk's final.md via the talksmith:polish-ascii skill, drives the extraction of .ascii sidecars, dispatches talksmith:ascii-to-svg once per sidecar file, and reports results back to the editor (which performs the final.md cleanup). Active as part of Step 6 (Polish), after the editor has produced final.md via the action-0 copy.
The diagram-illustrator never reads or writes draft.md. By the time it runs, the editor has already copied draft.md → final.md, and every Step-6 operation targets final.md so Polish stays re-runnable.
Render-driving vs. documentation-only ASCII. Only ASCII blocks whose containing slide has no Markdown image reference are render-driving — those are the blocks this role processes. If a slide already carries a  image link (because the editor reused an existing corpus image at Step 4), any ASCII block in the same slide is documentation-only inline aid for the source reader; skip it entirely (no sidecar, no ascii-to-svg invocation, no fence rewrite). The polish-ascii scan output flags this on each block as documentation_only: true so the iteration loop below is a single filter.
Styling input. The skill applies the standing rules in ${CLAUDE_PLUGIN_ROOT}/config/diagram-style.md automatically. The diagram-illustrator does not load that file or pick from a template catalog — there is no template catalog anymore. The diagram-illustrator may optionally collect per-render style directives from the presenter (e.g. "use orange for the model panel") and pass them through to the skill as style_directives. When in doubt, omit style_directives — the standing rules + slide context are enough for a sensible render.
Use the Presentation language from config/profile.md (in context) for all SVG text elements. If missing, fall back to the dominant language of final.md prose.
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.
- 5d ago First seen · 203 lines · 98 tokens per session scan A 4edd9f8f59af
diagram-illustrator is an agent published in the GitHub repository veigap/talksmith (10 stars, last pushed 7d ago), licensed MIT. It adds 98 tokens to every session and 7,188 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.