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 deerwork-ai/deer-workflow --skill workflow-creatorgit clone --depth 1 https://github.com/deerwork-ai/deer-workflowWrote 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/deerwork-ai/deer-workflow/workflow-creator)<a href="https://agentmods.dev/skills/deerwork-ai/deer-workflow/workflow-creator"><img src="https://agentmods.dev/badge/skills/deerwork-ai/deer-workflow/workflow-creator/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/deerwork-ai/deer-workflow/workflow-creator"><img src="https://agentmods.dev/badge/skills/deerwork-ai/deer-workflow/workflow-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.02978 |
| Opus 5.5 | $0.00026 | $0.01191 |
| Sonnet 5.5 | $0.00013 | $0.00596 |
| Haiku 4.5 | $0.00007 | $0.00298 |
Grade A, and why
workflow-creator 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.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deer Workflow Creator
Translate the user's task into one complete, runnable Deer Workflow ESM module. The module coordinates work; it does not pretend that Deer Workflow injects functions into its global scope.
Establish the target
Infer these decisions from the request and existing repository context:
- A kebab-case Workflow name and one-line description.
- The input object accepted by the Workflow.
- The final value returned to the caller.
- The durable artifact file or files the Workflow should create.
- The phases visible in lifecycle events.
- Which operations are deterministic coordination and which require an Agent Loop's judgment or tools.
- Whether work is independent fan-out, an item-by-item pipeline, or a global stage followed by another fan-out.
Ask a question only when a missing answer would materially change whether the Workflow reads or modifies user data. Otherwise make the smallest reasonable assumption and state it in a short code comment.
Read the actual contract
Read references/api.md before generating code. It is the source of truth for the currently implemented API.
Read references/patterns.md when the request involves concurrency, multiple Agent calls, structured output, verification, file changes, or nested Workflows.
The essential runtime model is:
- Import APIs explicitly from
@deerwork-ai/deer-workflow. - Export a pure-literal
metaobject containingname,description,phases, andexampleArgs. - Export an
asynchandler asdefaultor as namedrun. - Receive caller input as the handler's first argument, named
args. - Optionally receive the Workflow execution context as the second argument.
- Let
WorkflowRunnerprovide lifecycle, phase, event, and logging context through async-local state.
Do not generate the older destructured-injection signature:
export default async function ({ agent, parallel, args }) {}
args is not a JavaScript global. It is the first Handler parameter. Naming it
args preserves the Dynamic Workflow vocabulary without pretending the
current runtime mutates globalThis.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 319 lines · 66 tokens per session scan A 5b00e9783bf9
workflow-creator is a skill published in the GitHub repository deerwork-ai/deer-workflow (551 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 2,978 once invoked, about $0.0003 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.
Other skills, from other repositories
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
asking-user-questions
Use when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use before implementing a feature, a change in behavior, or a bug fix — however small. Not for questions, checks, or edits that change no behavior (typos, documentation or configuration only, mechanical refactors).
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.