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 tottinge/otter-skills --skill story-splitting-for-deliverygit clone --depth 1 https://github.com/tottinge/otter-skillsWrote 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/tottinge/otter-skills/story-splitting-for-delivery)<a href="https://agentmods.dev/skills/tottinge/otter-skills/story-splitting-for-delivery"><img src="https://agentmods.dev/badge/skills/tottinge/otter-skills/story-splitting-for-delivery/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/tottinge/otter-skills/story-splitting-for-delivery"><img src="https://agentmods.dev/badge/skills/tottinge/otter-skills/story-splitting-for-delivery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00104 | $0.02174 |
| Opus 5 | $0.00052 | $0.01087 |
| Sonnet 5 | $0.00021 | $0.00435 |
| Haiku 4.5 | $0.00010 | $0.00217 |
Grade A, and why
story-splitting-for-delivery 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 12d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Splitting for Delivery (Progressive Admission)
Core idea
This is the primary story-splitting skill. Build the end-to-end path first, fully closed. Then admit one safe case at a time. Everything not yet admitted stays rejected — invalid, unsupported, or not implemented. Each admission is a thin, testable, demonstrable, ideally deployable story.
This is related to walking skeleton / tracer bullet thinking, but the distinctive move is default-deny with progressive widening.
When this skill fits
Use it as the default whenever work is too big for one iteration or needs a delivery sequence. Progressive admission is especially natural when there is a clear cycle:
- message queue / event processing
- HTTP operations or API handlers
- batch file / import processing
- form fields and validation
- UI controls that enable one action after another
- schema or protocol versioning over time
- multi-path user journeys, roles, channels, or rule variants
If the admission boundary is not obvious, invent one from the variations in the work (paths, data shapes, rules, interfaces, roles). Do not fall back to component/task decomposition.
Use user-pov-sliced-stories only when the main need is user-invoke / user-uses-result formatting.
Target shape of each admission slice
A good admission slice:
- keeps the full end-to-end path wired
- admits exactly one new case, shape, type, field set, or rule
- continues to reject all non-admitted cases with a stable response
- is unit-testable and end-to-end testable
- produces an observable result that can be demonstrated without later admissions
- could be deployed without harming unhandled traffic
- leaves room to TDD and refactor after green
Progressive admission workflow
1) Name the admission boundary
State what is being admitted:
- message type / event type
- request shape
- file format or row shape
- UI action / command
- business rule variant
- schema version
Also name the default rejection:
- not implemented
- invalid input
- unsupported operation
- unknown type
What ships with it
3 files 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.
- 12d ago First seen · 235 lines · 104 tokens per session scan A 2ebad746013e
story-splitting-for-delivery is a skill published in the GitHub repository tottinge/otter-skills (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,174 once invoked, about $0.0005 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.