What is split-workflow-stages?

A workflow-maintenance skill that splits oversized workflow stages into smaller stages with one responsibility each. A workflow is an ordered set of automated tasks and dependencies.

Use it to audit workflow files, plan approved stage splits, apply the edits, and validate the resulting configuration.

It makes complicated stages easier to understand, verify, rerun, and debug without losing their input and output links.

How dancing-bear-show/dancing-bear configures Claude Code

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/split-workflow-stages/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/split-workflow-stages/github.svg)](https://agentmods.dev/skills/dancing-bear-show/dancing-bear/split-workflow-stages)

Your own site

<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/split-workflow-stages"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/split-workflow-stages/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/split-workflow-stages"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/split-workflow-stages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,600 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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.01600
Opus 5.5	$0.00028	$0.00640
Sonnet 5.5	$0.00014	$0.00320
Haiku 4.5	$0.00007	$0.00160

Measured yesterday against content hash 7900b7cc272c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

split-workflow-stages 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/split-workflow-stages/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Split Workflow Stages

Split oversized workflow stages into smaller, single-responsibility stages while preserving all depends_on, reads_from, and writes_to linkages.

When to Use

A stage description exceeds 80 lines
A stage both gathers raw data AND resolves/transforms it in the same block
A stage reads from 3+ distinct external sources AND produces 2+ distinct output files
A stage mixes "collect X" logic with "cross-reference Y against Z" logic
Downstream fact-checkers or validators cannot verify outputs because the reasoning is opaque
A stage is hard to re-run in isolation when debugging a workflow failure

Responsibility Heuristics

Heuristic	Threshold	Indicator
Description length	> 80 lines	Stage took on too much
Distinct data sources with distinct outputs	3+ sources AND 2+ output files	Classic gather+transform conflation
Gather + resolve in same description	Any	"Read the config AND resolve its interpolations" in one stage
Gather + cross-reference in same description	Any	"Collect findings AND cross-reference against the concern library" in one stage
Gather + validate in same description	Any	"Fetch the file list AND verify each file parses" in one stage
Validate + write corrections in same description	Any	"Check claims AND apply fixes" in one stage
Inline reference data > 10 rows	Any	Hardcoded substitution maps or ownership tables in description text

A stage with 2 or more matching heuristics is a strong split candidate.

Step 1 — Audit

Measure description length per stage:

python3 -I -c "
import sys, yaml
path = sys.argv[1]
d = yaml.safe_load(open(path))
for s in d.get('stages', []):
    lines = len((s.get('description') or '').strip().splitlines())
    reads = len(s.get('reads_from') or [])
    writes = len(s.get('writes_to') or [])
    flag = 'CANDIDATE' if lines > 80 or (reads >= 3 and writes >= 2) else 'ok'
    print(f'{flag:10} {s[\"name\"]:45} desc_lines={lines:4} reads={reads} writes={writes}')
" workflows/<domain>/<workflow>.yaml

Read the full file on GitHub · 165 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.

yesterday First seen · 165 lines · 70 tokens per session scan A 7900b7cc272c

Subscribe to this mod's changes

split-workflow-stages is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,600 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 2026-11-07.

Project management automation calendar cli gmail oauth2 outlook

split-workflow-stages next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
split-workflow-stagesdancing-bear-show/dancing-bear	Skill	7	yesterday	MIT	A	70	Claude Code
gogolafkfreund/nixos_config	Skill	32	yesterday	GPL-3.0	A	125	Claude Code, Codex
google-workspace-authbobmatnyc/claude-mpm	Skill	158	2mo ago	none	A	22	Claude Code
outlook-mcpmpalermiti/outlook-mcp	Skill	41	2d ago	MIT	A	96	Claude Code, Codex
olkrlrghb/olkcli	Skill	23	14d ago	MIT	A	28	Claude Code, Codex
ghealthGoogle-Health-API/google-health-cli	Skill	281	4mo ago	Apache-2.0	A	41	Claude Code, Codex
ghealth-sharedGoogle-Health-API/google-health-cli	Skill	281	4mo ago	Apache-2.0	A	22	Claude Code, Codex

dancing-bear: Skill for Claude Code