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/navraj007in/architecture-cowork-pluginWrote 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/navraj007in/architecture-cowork-plugin/export-diagrams)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/export-diagrams"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/export-diagrams/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/navraj007in/architecture-cowork-plugin/export-diagrams"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/export-diagrams.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 | $0.00015 | $0.01681 |
| Opus 5 | $0.00008 | $0.00840 |
| Sonnet 5 | $0.00003 | $0.00336 |
| Haiku 4.5 | $0.00002 | $0.00168 |
Grade A, and why
export-diagrams 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 12d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:export-diagrams
Trigger
/architect:export-diagrams — render all diagrams found in architecture-output/diagrams/ (default).
/architect:export-diagrams [diagram:X] — render one diagram only.
/architect:export-diagrams [diagrams:X,Y] — render a named subset.
/architect:export-diagrams [format:png|svg|both] — override output format (default: both).
Diagram names (matching canonical filenames without extension)
| Name | File |
|---|---|
solution-architecture |
solution-architecture.mmd |
deployment |
deployment.mmd |
sequence-auth |
sequence-auth.mmd |
er-diagram |
er-diagram.mmd |
service-communication |
service-communication.mmd |
agent-flow |
agent-flow.mmd |
sequence-payment |
sequence-payment.mmd |
Examples:
/architect:export-diagrams [diagram:er-diagram]
/architect:export-diagrams [diagrams:solution-architecture,deployment] [format:png]
/architect:export-diagrams [format:svg]
When a [diagram:...] or [diagrams:...] tag is present, render only the named diagrams. When absent, render all .mmd files found.
Purpose
After generating a blueprint with /architect:blueprint, this command renders all Mermaid diagrams (deliverable 4b) to PNG and SVG image files. Produces both light and dark theme variants, suitable for presentations, documentation, and wiki pages.
Workflow
Step 1: Find Diagrams
First, check architecture-output/_state.json for project.name.
Then, scan architecture-output/diagrams/ for all .mmd files — this is the canonical diagram folder. The expected canonical filenames are:
| File | Always present |
|---|---|
solution-architecture.mmd |
Yes |
deployment.mmd |
Yes |
sequence-auth.mmd |
Yes |
er-diagram.mmd |
When relational DB exists |
service-communication.mmd |
When 2+ backend services |
agent-flow.mmd |
When AI agents exist |
sequence-payment.mmd |
When payments exist |
Also check architecture-output/ top level for any .mmd files generated by older runs.
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.
- 12d ago First seen · 178 lines · 15 tokens per session scan A 7231ceb9d438
export-diagrams is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,681 once invoked, about $0.0001 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 commands, from other repositories
nyann:route-docs
Change documentation storage routing (local, Obsidian, Notion, or per-type split) and regenerate the doc scaffold to match.
spec-docs
Generate user-facing documentation from spec and implementation.
done
Finish a task - document, create PR or merge, close.
paper-trail-cascade
Acquire PDFs via the 8-source cascade (11 with opt-in extended sources) for a single ref by slug, or a batch filtered by state. Validates page 1 anti-homonymy on each download.
report
Render the latest audit as a deliverable report in Markdown / HTML / PDF / JSON / PNG.
nyann:apply
Apply an Infrastructure-as-Code change — the highest-stakes mutator in nyann; it can change real cloud infrastructure. Re-runs the plan, shows it, confirms, then applies. Unmistakably opt-in: apply is never the default and destructive applies require a second explicit confirm. For IaC apply intent only (not "apply a…