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 nikeyes/stepwise-dev --skill story-splittinggit clone --depth 1 https://github.com/nikeyes/stepwise-devWrote 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/nikeyes/stepwise-dev/story-splitting)<a href="https://agentmods.dev/skills/nikeyes/stepwise-dev/story-splitting"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/story-splitting/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/nikeyes/stepwise-dev/story-splitting"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/story-splitting.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 | $0.00050 | $0.04013 |
| Opus 5.5 | $0.00020 | $0.01605 |
| Sonnet 5.5 | $0.00010 | $0.00803 |
| Haiku 4.5 | $0.00005 | $0.00401 |
Grade A, and why
story-splitting 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Splitting Expert
Expert at detecting when work is too big and applying proven splitting heuristics to break it down into small, safe, valuable increments.
When to Use This Skill
Use when:
- Story has obvious red flags: "and", "or", "manage", "handle", "including"
- User describes multiple features bundled together
- Story feels vague or too large
- User asks "how to split this story"
Do NOT use when:
- Story is already small and focused (< 1 day work)
- Feature needs layered analysis without obvious split points (use hamburger-method instead)
- User asks HOW to implement (use micro-steps-coach instead)
Detection: Red Flags in Stories
Always scan for these linguistic indicators that signal a story is too big:
1. Coordinating Conjunctions: "and", "or", "but", "yet"
- "Users can upload and download files" → Split into 2 stories
- "Admin can view or edit users" → Split into 2 stories
2. Action-Related Connectors: "manage", "handle", "support", "process", "administer"
- "Admin can manage users" → Hides create, edit, delete, list
- "System handles payments" → Hides initiate, process, refund, report
3. Sequence Connectors: "before", "after", "then", "while", "when"
- "Save work before submitting" → 2 separate stories
- "Process payment then send receipt" → 2 steps, 2 stories
4. Scope Indicators: "including", "as-well-as", "also", "additionally", "plus"
- "Notifications via email and SMS" → Split channels
- "Report including charts and exports" → Split outputs
5. Option Indicators: "either/or", "whether", "optionally", "alternatively"
- "Login with password or Google" → 2 authentication methods
- "Export to CSV or PDF" → 2 format stories
6. Exception Indicators: "except", "unless", "however", "although"
- "Delete account unless admin" → Base case + exception
When you spot these words, immediately flag the story as too big.
Decision Tree: Red Flag → Recommended Technique
What ships with it
1 file 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 · 431 lines · 50 tokens per session scan A e03cd5e43955
story-splitting is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 50 tokens to every session and 4,013 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.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…