agentmods.dev

work-in-slice

work-in-slice is a skill for Claude Code from paulinevos/claude-stuff. It costs 56 tokens per session (592 once invoked), scanned A, original, MIT.

A workflow for completing one focused change in a Jujutsu workspace, recording each logical step as its own revision. Jujutsu is a version-control system, similar to Git, that tracks changes and bookmarks.

In plain words
What is it for?
Use it to implement a small slice of work, maintain a reviewable sequence of revisions, keep a bookmark current, and hand the result back without pushing it.
Why use it?
It keeps a worker's changes isolated and easy to review, while ensuring each revision builds and passes tests on its own.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the jj-workflow plugin — 4 skills shipped together

not rated 64repo +1 changed 11d ago A scan 56 tokens original MIT

Good fit Use it to implement a small slice of work, maintain a reviewable sequence of revisions, keep a bookmark current, and hand the result back without pushing it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/paulinevos/claude-stuff/work-in-slice
View source ↗ paulinevos/claude-stuff
Install

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.

Any agent
npx skills add paulinevos/claude-stuff --skill work-in-slice
Clone the repo
git clone --depth 1 https://github.com/paulinevos/claude-stuff

Made for: Claude Code.

Or install jj-workflow, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for work-in-slice

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulinevos/claude-stuff/work-in-slice/github.svg)](https://agentmods.dev/skills/paulinevos/claude-stuff/work-in-slice)
Your own site
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/work-in-slice"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/work-in-slice/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.

agentmods 80×15 button for work-in-slice

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/work-in-slice"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/work-in-slice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00592
Opus 5.5 $0.00022 $0.00237
Sonnet 5.5 $0.00011 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 11d ago against content hash 7584134b4b46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

work-in-slice 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 11d 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.

plugins/jj-workflow/skills/work-in-slice/SKILL.md · 51 lines

What it actually says

work-in-slice

Own only the assigned workspace, bookmark, and descendant change IDs. Work there, never in another worker's directory.

  1. Confirm @ is an empty change on the assigned base:

    jj workspace root
jj log -r '@ | @-' --no-graph -T 'change_id.short() ++ " " ++ if(empty, "(empty) ") ++ description.first_line() ++ "\n"'

    If it is not, stop and tell the orchestrator.

  2. Make one logical, independently passing revision at a time:

    jj status
jj describe -m 'Add retry policy to HttpClient'
jj new

    Use an imperative, capitalised subject without a period; a body explains why. Create the bookmark after the first revision with jj bookmark create <slice> -r @-, then move it after every revision with jj bookmark move <slice> --to @-.

  3. Fold fixes rather than stacking follow-ups: jj squash --into <change-id>; use jj absorb for line-based ancestor fixes, jj split to separate work, jj describe -r to reword, and jj rebase -r ... -B ... to reorder. Refer to revisions by change ID, not commit ID.

  4. When the base moves: jj git fetch && jj rebase -b <slice> -o <base>; resolve recorded conflicts in their revision (jj new, edit, jj squash), then return to the tip with jj new <slice>. A stale-workspace error means stop and use sync-workspace.

  5. Before hand-off, leave @ empty, run jj status, ensure all slice revisions are described and conflict-free, and report the workspace, bookmark, and ordered revision list. Do not push or forget the workspace.

Never use --ignore-immutable. Snapshot with jj status before pausing; rewriting an active descendant's ancestor risks a divergent recovery.

If navi --version succeeds, jj-navi can handle workspace navigation; navi switch and navi doctor are safe for a worker, while navi list and navi merge belong to the orchestrator. Offer the install when it is missing rather than running it. None of the steps above change.

Files

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.

Changes

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.

  1. 11d ago Changed · +6 lines · +12 tokens per session 7584134b4b46
  2. 21d ago Changed · -54 lines · -128 tokens per session 43ed80884d0c
  3. 1mo ago First seen · 99 lines · 172 tokens per session scan A 84e526e72d3a

Subscribe to this mod's changes

work-in-slice is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 592 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 2026-09-10.

CommitsGit and workflow
Related

Other skills, from other repositories

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 48 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

repo-sync

Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.

davidondrej/skills · 25 tokens

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens

git-commit-writer

Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.

mergisi/awesome-openclaw-agents · 53 tokens