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 commands/hesreallyhim/ultracode-workflows/wf-diagramgit clone --depth 1 https://github.com/hesreallyhim/ultracode-workflowsWrote 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/hesreallyhim/ultracode-workflows/wf-diagram)<a href="https://agentmods.dev/commands/hesreallyhim/ultracode-workflows/wf-diagram"><img src="https://agentmods.dev/badge/commands/hesreallyhim/ultracode-workflows/wf-diagram.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 | $0.00019 | $0.00442 |
| Opus 5 | $0.00010 | $0.00221 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
wf-diagram 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.
What it actually says
/wf-diagram
Diagram the workflow the user named in $ARGUMENTS.
Resolve the target: if $ARGUMENTS is a path to a .js file, use it; if it's a bare name, use ${CLAUDE_PLUGIN_ROOT}/workflows/<name>.js; if it names a file in this project's .claude/workflows/, use that.
Then run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/diagram-workflow.mjs" <resolved-path>
This prints a terminal rendering — one bounding card per phase, edges between cards, loops as a rail in the left margin. Relay it to the user inside a fenced code block so the monospace alignment survives; the box-drawing columns break if it is emitted as prose.
Add --md instead when the user wants Mermaid to paste into GitHub, a PR, or docs. Do not print both.
Reading the output:
·one agent,⇉a parallel fan-out,▸a nested sub-workflow,↺a loop.×4is an exact width;×0–3 ⁇and×N ⁇mean the count is runtime-dependent or could not be resolved statically.inheritedin the effort column means the call site sets no effort and takes the session's.- A phase that appears twice with
(revisit)is the same phase re-entered, not a new stage.
The tool statically parses the script's AST and never evaluates the workflow body, so do not supply runtime args. If the tool reports a dynamic dispatcher, explain that it can show the statically discoverable targets but the target selected for a particular run is decided at runtime. An unknown upper bound means only that static analysis could not prove a cap; do not call it an infinite or unbounded run.
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 · 30 lines · 19 tokens per session scan A 16c6da440950
wf-diagram is a command published in the GitHub repository hesreallyhim/ultracode-workflows (3 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 442 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
diagnose-underperformer
Diagnose why a specific Google Ads or Meta Ads campaign / ad set / ad is underperforming and prescribe the next concrete action. Use when the user says something like "why is X not converting?", "this campaign is wasting money", or "why are impressions so low?". Read-only — no changes are made.
edit-meta-creative
Edit a Meta ad's creative content — landing page URL, primary text, headline, description, CTA, link description — across one ad or many. Use when the user says "change the URL on my ads", "update the copy", "swap the CTA", or anything that changes what an existing Meta ad shows. Meta does not allow in-place creative…
save
Save this conversation as a new or existing reusable context.
launch-meta-campaign
Launch a complete Meta Ads campaign — campaign, ad set, and ad(s) — built paused and ready to review. Use when the user wants a new Facebook/Instagram campaign.
launch-pmax
Launch a Google Ads Performance Max campaign with a complete asset group, audience signals, and (for ecom) listing groups. Built paused for review. Use when the user wants a new PMax campaign.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.