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 white1024/agent-nextup --skill slice-workgit clone --depth 1 https://github.com/white1024/agent-nextupWrote 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/white1024/agent-nextup/slice-work)<a href="https://agentmods.dev/skills/white1024/agent-nextup/slice-work"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/slice-work/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/white1024/agent-nextup/slice-work"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/slice-work.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 | $0.00054 | $0.01043 |
| Opus 5.5 | $0.00022 | $0.00417 |
| Sonnet 5.5 | $0.00011 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
slice-work 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slice-work — turn agreed scope into schedulable tasks
Goal: the work exists as tasks in this workspace, each one a slice that can be finished in one session and shown working on its own, with dependsOn naming exactly what must land first — so "Next steps" and list_tasks { ready: true } always point at something that can actually start.
Start from a settled scope. If what "done" means is still open, settle it first: call the Skill tool with align-scope.
1. Read what is already there
- The open tasks (
list_tasks) and the recent decisions, so new tasks neither duplicate nor contradict them. - The project's vocabulary —
GLOSSARY.mdat the project root if there is one, otherwise the vocabulary files in memory — and use its words in every title. - With the spec module on (
validate_task_specsis in your tool list): the current specs of the capabilities this work touches (list_specs,get_spec).
Done when you can name every existing task this work touches.
2. Draft the slices
- Vertical, not horizontal. Each task cuts a narrow path through every layer it needs and can be shown working on its own. "A user can export one report as CSV" is a slice; "write the export backend" is a layer.
- One session each. A slice that will not fit gets cut again.
- Prefactor first. When the existing structure makes the change awkward, the clean-up is its own task and the feature depends on it.
- Expand → migrate → contract for a mechanical change that reaches across the whole project (a rename, a reshaped shared type): add the new form beside the old, move callers over in batches small enough that each stays green, remove the old form last — chained with
dependsOn. - For each task write a title naming what it delivers, a description saying what it delivers end to end and how anyone will know it works, and its blockers: only the tasks that genuinely gate it. Describe behaviour rather than files — the files shift as the work does.
Done when every agreed outcome is covered by at least one task and every blocker points at a task in the draft or already in the store.
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.
- 4d ago First seen · 67 lines · 54 tokens per session scan A 83ed7284b675
slice-work is a skill published in the GitHub repository white1024/agent-nextup (2 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 1,043 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 2026-10-19.
Other skills, from other repositories
project-scanner
Project introspection — detect languages, frameworks, database, structure, scale, auth, CI/CD.
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md.
gsd-ns-manage
Invoke this Pi skill with /skill:gsd-ns-manage.
gsd-resume-work
Resume work from previous session with full context restoration.
02-user-stories
Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.
07-epic
Produces or refines an outcome-based Epic for a product backlog. Use when the user wants to frame, review, resume, or persist an Epic. Not for Product Briefs, User Stories, or implementation.