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 skills add patleeman/neon-pilot --skill dynamic-workflowsgit clone --depth 1 https://github.com/patleeman/neon-pilotWrote 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/skills/patleeman/neon-pilot/dynamic-workflows)<a href="https://agentmods.dev/skills/patleeman/neon-pilot/dynamic-workflows"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/dynamic-workflows/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/skills/patleeman/neon-pilot/dynamic-workflows"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/dynamic-workflows.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 | $0.00038 | $0.02049 |
| Opus 5.5 | $0.00015 | $0.00820 |
| Sonnet 5.5 | $0.00008 | $0.00410 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
dynamic-workflows 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 2mo 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dynamic Workflows
Use the workflow tool when the task is better handled as an explicit coordinator than as one long foreground turn. Good fits include parallel investigation, multi-phase validation, fanout over files/modules, and workflows where progress should remain visible in the transcript and Workflows page.
Do not use workflow for a simple one-step edit or command. Normal foreground work is cheaper and easier to inspect for small tasks.
Runtime Contract
The script field is the body of an async function. Do not use module.exports, export default, or top-level module syntax.
The host wraps scripts like this:
'use strict';
(async () => {
// script body goes here
})();
Available globals:
| API | Purpose |
|---|---|
workflow.phase(name) |
Set the active phase shown in persistence and transcript status. |
workflow.agent(input) |
Spawn a daemon-backed subagent from the desktop/product runtime. |
workflow.map(items, fn) |
Run async work across items; workflow.agent calls are capped by workflow settings. |
workflow.log(message, data?) |
Add a structured workflow event. |
workflow.finish(result) |
Set the final workflow result. |
args |
The tool input args value. |
console.log(...) |
Routed to workflow.log. |
The script itself is orchestration-only. It does not receive direct shell, filesystem, app internals, process, or require access. Real work should happen in subagents.
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.
- 2mo ago First seen · 248 lines · 38 tokens per session scan A cc0bec997ac1
dynamic-workflows is a skill published in the GitHub repository patleeman/neon-pilot (23 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 2,049 once invoked, about $0.0002 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 2026-08-30.
dynamic-workflows compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dynamic-workflowspatleeman/neon-pilot | Skill | 23 | 3mo ago | MIT | A | 38 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |