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/insideout-ai/make-it-work/slice-the-epicnpx skills add insideout-ai/make-it-work --skill slice-the-epicgit clone --depth 1 https://github.com/insideout-ai/make-it-workWrote 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/insideout-ai/make-it-work/slice-the-epic)<a href="https://agentmods.dev/skills/insideout-ai/make-it-work/slice-the-epic"><img src="https://agentmods.dev/badge/skills/insideout-ai/make-it-work/slice-the-epic.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 | $0.00168 | $0.03530 |
| Opus 5 | $0.00084 | $0.01765 |
| Sonnet 5 | $0.00034 | $0.00706 |
| Haiku 4.5 | $0.00017 | $0.00353 |
Grade A, and why
slice-the-epic 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slice the Epic
Slicing is the practice of breaking a large requirement into smaller pieces ("slices") that each deliver a usable, demonstrable increment on their own. Thinner slices mean shorter cycle time, faster feedback, easier estimation, and lower risk — because uncertainty gets resolved a little at a time instead of all at once at the end. This skill turns a big, vague requirement into a set of small, well-formed user stories.
The process
Work through these steps in order. Don't treat them as a rigid checklist to recite back to the user — think of them as the reasoning a good product-minded engineer or PO would apply.
1. Understand the requirement
Get the actual requirement text. If the user gives a Jira/Confluence link or ticket ID and a connector is available, fetch it. If they paste a requirement or epic description, work from that directly.
If the requirement is reasonably concrete, proceed straight to slicing — don't interrogate the user with a round of questions just for the sake of it. Only pause to ask (one focused question at a time, not a list) when something is genuinely blocking, e.g.: the requirement has no identifiable user or workflow at all, or it mixes several unrelated features together and it's unclear which one to slice.
Also check whether the requirement is already written as a user story with its own Given/When/Then acceptance criteria (rather than a loose paragraph). If so, look at whether each existing AC could stand on its own as a slice — this is frequently the fastest and most natural path to slicing, since the seams are already drawn by whoever wrote the ACs, and it can save you from forcing one of the techniques in step 2 onto a shape that doesn't need it.
2. Pick slicing technique(s)
If step 1 turned up existing acceptance criteria that already slice cleanly on their own, you can use that directly — it doesn't need to compete with the techniques below. Otherwise, here are the techniques, listed in priority order — when more than one would work, prefer the one higher in this list:
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 · 130 lines · 168 tokens per session scan A a831886a1ca8
slice-the-epic is a skill published in the GitHub repository insideout-ai/make-it-work (11 stars, last pushed 24d ago), licensed MIT. It adds 168 tokens to every session and 3,530 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
check-docs
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
review-agent-config
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
deep-test
Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification.
cold-start
Bootstrap the ai/ knowledge layer for a repo that has none — draft the MODULEMAP, diagrams, and guide docs as [inferred] for a human to audit, touching no source code. Use when the maps are still placeholders or the user asks to cold-start, bootstrap, or onboard a repository.
adversarial-audit
Deep, judgement-based adversarial code audit — hunts for stale cross-references, unescaped interpolation, platform gaps, generated-file ownership conflicts, and cross-module consistency rot that no mechanical check can catch. Read-only; writes a dated findings report.
implement-spec
Implement a spec from ai/lab/specs/ exactly as written — zero design decisions, stop-and-report on any spec-vs-reality conflict, tests are the definition of done. Built for lighter implementation models.