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 agentmods add skills/acendas/shipyard/splitting-storiesnpx skills add Acendas/shipyard --skill splitting-storiesgit clone --depth 1 https://github.com/Acendas/shipyardWrote 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/acendas/shipyard/splitting-stories)<a href="https://agentmods.dev/skills/acendas/shipyard/splitting-stories"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/splitting-stories.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00014 | $0.02944 |
| Opus 5 | $0.00007 | $0.01472 |
| Sonnet 5 | $0.00003 | $0.00589 |
| Haiku 4.5 | $0.00001 | $0.00294 |
Grade A, and why
splitting-stories 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 5d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Splitting Stories
A feature or task that is too big does not get smaller by being given a smaller estimate — it gets smaller by being split into independently valuable pieces. The default failure mode for an LLM orchestrator is to split horizontally (UI / API / DB as separate stories), which produces tasks that are technically smaller but none of which is independently demoable. This skill exists to force vertical slicing.
The output is a list of split candidates, not opinions — concrete child stories/tasks each with a one-line user-observable outcome and the splitting pattern that produced it.
When to Invoke
| Caller | Trigger |
|---|---|
/ship-discuss Phase 2 (Viability Gate) |
When the SPLIT signal fires ("multiple stories in a trench coat") or BUILDABLE/SIZED fails on size grounds |
/ship-discuss Phase 1.5b challenge |
When the user describes a feature whose acceptance criteria already exceed what fits in one sprint |
/ship-sprint Stage 3 (task decomposition) |
When a behavior draft fails the "and" test or any of the 11 patterns fires |
/ship-sprint Stage 5 (effort) |
When a task is estimated effort: L and the L-confirmation checklist is uncertain |
| Manual / ad-hoc | When the user says "this feels too big" |
Skip for trivial inputs (single AC, single touchpoint, S effort with one obvious Red step). The splitting overhead exceeds value.
Inputs
story_text— the feature/task draft to split (markdown). May be a/ship-discussdraft, an existing feature spec, or a task draft from/ship-sprintStage 1.acceptance_criteria— the AC list for the input, if separate from the draft.level—feature(splitting a story into smaller stories) ortask(splitting a task into smaller tasks). Defaulttask.domain_hints— optional list of domain tags (["payments", "auth", "external-api", "ui"]) that bias which patterns fire first.data_dir— for reading<SHIPYARD_DATA>/codebase-context.mdto ground splits in the actual stack.
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.
- 5d ago First seen · 176 lines · 14 tokens per session scan A 94ccf8c3aa00
splitting-stories is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 24d ago), licensed MIT. It adds 14 tokens to every session and 2,944 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
break-complex-projects-into-milestones
How to use AI to generate structured Work Breakdown Structures (WBS), 4-week critical path roadmaps, and verifiable milestone deliverables.
iterate-step-by-step
How to use the 4-Turn Conversational Scaffolding framework to build complex code, strategy, and content incrementally without token exhaustion or quality degradation.
write-epic
Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.
write-user-story
Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.
engenharia-de-requisitos
Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…
engenharia-de-requisitos
Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…