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-newgit 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-new)<a href="https://agentmods.dev/commands/hesreallyhim/ultracode-workflows/wf-new"><img src="https://agentmods.dev/badge/commands/hesreallyhim/ultracode-workflows/wf-new.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 | $0.00020 | $0.00417 |
| Opus 5 | $0.00010 | $0.00209 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
wf-new 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.
What it actually says
/wf-new
The user wants a new Workflow script for: $ARGUMENTS
Invoke the workflow-authoring skill as a pattern composer and follow its procedure end to end:
- Decide whether the task warrants a reusable multi-agent workflow; recommend a simpler prompt when it does not.
- Show a compact orchestration brief, one recommended catalog composition, and at most two meaningful alternatives. Offer quick/balanced/deep cost presets, let the user override their individual levers, and identify whether token ceiling or duration target wins when both are tight. Include agent-count, peak-width, sequential-depth, budget-guard, and duration assumptions; explain which figures are exact, ranged, or unknown.
- Select two or three nearest marketplace workflows as structural, trust, and scale precedents. Extract their invariants rather than copying their agent counts or phase names.
- Design the structured dataflow, failure meanings, convergence/coverage rule, and mutation boundary before writing prompts.
- Draft the smallest topology that preserves those invariants, consulting the skill's API-contract reference only for harness details.
- Review the completed source without executing it. In this repository checkout, run the repository parser gate against the actual authored path, not the default catalog command.
- Generate an advisory static terminal diagram, relay it inside a fenced plain-text code block, explain the visible composition patterns and exact/ranged/unknown widths, and offer one focused revision pass before delivery.
- Save the script to this project's
.claude/workflows/<name>.js(create the directory if needed) and tell the user how to invoke it, which catalog patterns informed it, and what remains uncertain.
If $ARGUMENTS is empty, ask the user what the workflow should accomplish before starting.
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 · 22 lines · 20 tokens per session scan A 3b34b9fad311
wf-new is a command published in the GitHub repository hesreallyhim/ultracode-workflows (2 stars, last pushed 27d ago), licensed MIT. It adds 20 tokens to every session and 417 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
export-md
Export this session's conversation to a markdown file.
health
Check running Claude Code or Codex sessions, find zombies, offer to clean up safely.
quick
Quick 10-second context health check with quality score and top issues.
no-cape
Manually load a no-cape discipline skill and apply it to the current work.
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.