agentmods.dev

dancing-bear: Skill for Claude Code

.claude/skills/write-workflow/SKILL.md

write-workflow is a skill for Claude Code from dancing-bear-show/dancing-bear. It costs 51 tokens per session (4,393 once invoked), scanned A, original, MIT.

A guided authoring tool for creating workflow files in YAML, a text format for structured configuration. It gathers requirements, drafts the file using project conventions, checks it with the workflow engine, and saves it.

In plain words
What is it for?
Use it to create a new project workflow, define its inputs and behaviour, validate the result, and write it into the workflows directory.
Why use it?
It reduces the mistakes involved in turning a plain-language multi-step task into a valid reusable workflow.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

This is dancing-bear-show/dancing-bear's own configuration. It tells Claude Code how to work on dancing-bear itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dancing-bear configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/workflow lint <output_path> --check-commands.

not rated 7repo yesterday A scan 51 tokens original MIT
View source ↗ dancing-bear-show/dancing-bear
Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/skills/write-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

Made for: Claude Code.

Wrote 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.

agentmods badge for write-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/write-workflow/github.svg)](https://agentmods.dev/skills/dancing-bear-show/dancing-bear/write-workflow)
Your own site
<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/write-workflow"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/write-workflow/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.

agentmods 80×15 button for write-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/write-workflow"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/write-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.04393
Opus 5.5 $0.00020 $0.01757
Sonnet 5.5 $0.00010 $0.00879
Haiku 4.5 $0.00005 $0.00439

Measured yesterday against content hash 351c34da68c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-workflow 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 yesterday.

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.

.claude/skills/write-workflow/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

write-workflow

Author a new workflow YAML from a plain-language description. Interviews the user for requirements, drafts a well-formed YAML that follows project conventions, validates it with the workflow engine, and writes the final file.

When to Use

  • User says "write a workflow for X", "create a workflow that does Y", "I want a workflow to Z"
  • User wants to automate a multi-step task as a reusable YAML pipeline
  • User needs a new entry in workflows/ that integrates with the /workflow skill

Relationship to the workflow-author agent

This repo also defines a workflow-author agent (.claude/agents/workflow-author.md). Use this skill for interactive authoring in the current session; delegate to the agent when workflow authoring is one step inside a larger task and you want it done out-of-context.

Step 1 — Interview

Ask the user (or infer from their request) the following. If the initial request already carries enough detail, infer the answers and skip asking.

  1. Name: short kebab-case identifier (e.g. mail-label-audit, resume-render-sweep)

  2. Description: what does this workflow do in one sentence?

  3. Trigger params: what inputs must the user supply at run time? (e.g. source_root, pr_number, min_coverage). List each param and what it represents.

  4. Stages: what are the logical steps? For each stage, infer:

    • What kind of work is it? (gather / propose / execute / validate / publish / sub-workflow — see guide below)
    • Which agent role fits best? (see role guide below)
    • Does it depend on the output of an earlier stage?
    • Should a human review and approve the output before the workflow continues? (→ human_gate: true)

  5. Fan-out: does any stage need to run once per item in a dynamic list (e.g. once per file, once per directory group)?

  6. Existing fragments: should any shared fragment from workflows/shared/ be included?

    Available fragments (pick any that fit the workflow shape). Each fragment's header comment documents its expected prefix, the stage names it injects, and the trigger.params the caller must set — read the file before including it.

Read the full file on GitHub · 449 lines

Changes

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.

  1. yesterday First seen · 449 lines · 51 tokens per session scan A 351c34da68c9

Subscribe to this mod's changes

write-workflow is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 4,393 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 2026-11-07.

Project managementautomationcalendarcligmailoauth2outlook
Related

write-workflow compared with skills from other repositories

write-workflow next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
write-workflowdancing-bear-show/dancing-bearSkill7yesterdayMITA51Claude Code
gogolafkfreund/nixos_configSkill32yesterdayGPL-3.0A125Claude Code, Codex
google-workspace-authbobmatnyc/claude-mpmSkill1582mo agononeA22Claude Code
outlook-mcpmpalermiti/outlook-mcpSkill412d agoMITA96Claude Code, Codex
olkrlrghb/olkcliSkill2314d agoMITA28Claude Code, Codex
ghealthGoogle-Health-API/google-health-cliSkill2814mo agoApache-2.0A41Claude Code, Codex
ghealth-sharedGoogle-Health-API/google-health-cliSkill2814mo agoApache-2.0A22Claude Code, Codex