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.
git clone --depth 1 https://github.com/jessepike/diagram-forgeWrote 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/commands/jessepike/diagram-forge/iterate)<a href="https://agentmods.dev/commands/jessepike/diagram-forge/iterate"><img src="https://agentmods.dev/badge/commands/jessepike/diagram-forge/iterate/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/commands/jessepike/diagram-forge/iterate"><img src="https://agentmods.dev/badge/commands/jessepike/diagram-forge/iterate.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 | $0.00010 | $0.00312 |
| Opus 5.5 | $0.00004 | $0.00125 |
| Sonnet 5.5 | $0.00002 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
iterate 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 1mo 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.
What it actually says
Diagram Iteration Workflow
You are helping the user refine an existing diagram using the diagram-forge edit_diagram MCP tool.
Steps
-
Verify the image: Confirm the provided image_path exists using the Read tool (it can read images).
-
Gather edit instructions: If the user provided instructions, use them. Otherwise, ask what they want to change. Common edits include:
- Add/remove components
- Change layout or grouping
- Update labels or text
- Adjust colors or styling
- Add connections or data flows
- Improve legibility
-
Select provider: Use the same provider that generated the original diagram if known. Gemini and OpenAI both support editing.
-
Execute edit: Call
edit_diagramwith the image path, edit instructions, and provider. -
Present results: Show the new output path. Offer to iterate further or compare with the original.
Guidelines
- Show the edit prompt before executing
- Mention that edits may not be pixel-perfect — sometimes regenerating with an updated prompt works better
- If multiple rounds of editing degrade quality, suggest regenerating from scratch with a refined prompt
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.
- 1mo ago First seen · 39 lines · 10 tokens per session scan A 84ed7e0d1350
iterate is a command published in the GitHub repository jessepike/diagram-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 312 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
find
Quick gallery search. Use when user runs /meigen:find with keywords to browse inspiration.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
design-audit
Audit the rendered design of live sites. Evidence capture first, then one critique per site. Argument is a URL, a repo name, or all.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.
mockups-generate
Generate dashboard mockups.