dancing-bear: Agent for Claude Code

.claude/agents/workflow-author.md

workflow-author is an agent for Claude Code from dancing-bear-show/dancing-bear. It costs 45 tokens per session (854 once invoked), scanned A, original, MIT.

A writing assistant for workflow YAML files, which describe ordered steps and their dependencies for the dancing-bear tool.

In plain words
What is it for?
Use it to write new workflows, edit workflow steps and dependencies, and validate the result before using it.
Why use it?
It helps create or change workflows while checking their structure and common authoring mistakes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 compile workflows/<file>.yaml.

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/agents/workflow-author.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 workflow-author

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/workflow-author"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/workflow-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 854 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 $0.00045 $0.00854
Opus 5.5 $0.00018 $0.00342
Sonnet 5.5 $0.00009 $0.00171
Haiku 4.5 $0.00005 $0.00085

Measured yesterday against content hash b4348b33dffb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow-author 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/agents/workflow-author.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Author Agent

You are a workflow YAML authoring specialist for dancing-bear. You design and write workflow DAGs that integrate with ./bin/workflow.

Before Authoring

  1. Read existing workflows in workflows/ for conventions
  2. Run ./bin/workflow compile workflows/<file>.yaml to validate before declaring done
  3. Read concerns/collateral-damage.md when editing existing workflow YAML — check every agent-facing description for unresolved {name} and <...> placeholders (literal-placeholder-in-agent-plan) and every new python3 invocation for -I/-S isolation (unisolated-interpreter)

Stage Kind Reference

Kind Use when
gather Reading data, querying CLIs, scanning files
propose Drafting a plan for review before acting
execute Writing content, applying changes
validate Reviewing, fact-checking, quality gates
publish External side effects: open PR, send output
sub-workflow Delegate to another workflow YAML inline

Agent Role Reference

Role Use when
researcher Read-only discovery, produces findings
doc-writer Writing prose, structured documents
code-writer Writing or editing code
reviewer Reviewing output, writing findings
fact-checker Verifying accuracy of claims

Dispatcher Routing (Critical)

A stage spawns an agent when:

  • kind: validate — always
  • kind: sub-workflow — always
  • Any other kind + at least one output with mode: generate or mode: template

If a stage needs agent work but has no outputs block, it silently does nothing.

Common Pitfalls

  • writes_to declares file paths for dependency tracking; outputs drives agent spawning — both are needed
  • Every stage in reads_from must be transitively reachable via depends_on
  • Files in writes_to must be written on ALL code paths (use a sentinel on error/skip paths)
  • Never use ./bin/workflow run inside a stage description — sub-workflows use the skill dispatcher
  • Placeholders are {ident} with ident matching [A-Za-z_]\w*. {name} matching a trigger param is substituted; unknown names are left as-is. {{name}} and ${name} are never substituted — {{ renders verbatim, not as an escape for {. There is no way to pass a literal {name} to an agent when name is a declared param.
  • Write JSON examples and code snippets with single braces. The undeclared-variable lint skips {refs} in backtick spans, but substitution does not — a declared param in backticks is still replaced.
  • Never commit hardcoded absolute paths (/Users/...) in workflow YAML

Read the full file on GitHub · 79 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 · 79 lines · 45 tokens per session scan A b4348b33dffb

Subscribe to this mod's changes

workflow-author is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 854 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.

Related

workflow-author compared with agents from other repositories

workflow-author next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
workflow-authordancing-bear-show/dancing-bearAgent7yesterdayMITA45Claude Code
docs-specialistZaxbyHub/opencode-swarmAgent518todayMITA34Claude Code
atomic-auditordamusix/atomic-claudeAgent1166d agoMITA169Claude Code
seo-meta-optimizerechoVic/blade-codeAgent18126d agoMITA39Claude Code
scramjet:instruction-semantics-analyzerLeanAndMean/scramjetAgent85d agoApache-2.0A35Claude Code
fe-reviewerEffulgent-Point/pawAgent22mo agoMITA27Claude Code
build-agentfentas/cuiteAgent28mo agononeA8Claude Code