A control for sending self-contained coding tasks to the slashwork offload network, where another machine can do the work. It also lets you turn this routing on or off and check its status.

Use it to set up authentication, enable or pause task routing for a project, view credits and status, and manage offloaded subagent work.

It can move suitable tasks away from the current session while leaving tasks that need local files or context to run locally.

work — Skill for Claude Code by slashwork-sh/plugin

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/slashwork-sh/plugin

agentmods

npx agentmods add skills/slashwork-sh/plugin/work

Made for: Claude Code.

Or install slashwork-work, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/slashwork-sh/plugin/work/github.svg)](https://agentmods.dev/skills/slashwork-sh/plugin/work)

Your own site

<a href="https://agentmods.dev/skills/slashwork-sh/plugin/work"><img src="https://agentmods.dev/badge/skills/slashwork-sh/plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/slashwork-sh/plugin/work"><img src="https://agentmods.dev/badge/skills/slashwork-sh/plugin/work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,411 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 3 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.

Model	Per session	Once invoked
Fable 5.1	$0.00232	$0.03411
Opus 5.5	$0.00093	$0.01364
Sonnet 5.5	$0.00046	$0.00682
Haiku 4.5	$0.00023	$0.00341

Measured 2mo ago against content hash 9042f75b7c93, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

work scanned grade C with 3 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 2mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

( umask 077; mkdir -p "$HOME/.slashwork"; printf '%s' "$TOKEN" > "$TOKENFILE"; chmod 600 "$TOKENFILE" )

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

S=./.claude/settings.local.json

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

START=$(curl -sS --max-time 20 -X POST "$BASE/auth/cli/start")

plugins/work/skills/work/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/work, the slashwork offloader

Route this session's self-contained subagent spawns to the slashwork offload network. The plugin's PreToolUse hook (hooks/intercept.sh) does the routing; this skill sets up and controls it. The hook is conservative by construction: only a prompt it judges confidently self-contained is routed, everything else (and every failure, cold pool, or slow earner) falls through to the local spawn exactly as it would have run. Routing costs credits per task by class; a new account starts with enough to try it. Earn credits back with the slashwork-earn plugin (/earn).

$ARGUMENTS is one of:

init [--reauth]: one-time setup. Authenticate in the browser (token to ~/.slashwork/token). Interception is on by default once the token exists. --reauth forces a fresh sign-in even if a token exists.
on: resume interception for the current project (removes the off override; no auth step).
off: pause interception for the current project.
empty (a bare /work): show status: token, interception, credits, and the dashboard link. With no token yet, run the init routine instead, so a bare /work is all a new user needs.

Interception is ON BY DEFAULT: the hook routes unless SLASHWORK_INTERCEPT is exactly "0" (and stays inert with no token). off writes SLASHWORK_INTERCEPT="0" into the project's .claude/settings.local.json env block; on removes that override. Claude Code applies the env block when a session starts, so a change takes effect from the NEXT session in this project. Say so whenever you flip it.

Resolution order (same as the earn plugin):

token: SLASHWORK_TOKEN env, then ~/.slashwork/token, else run /work init.
base_url: settings.json base_url in the cwd, then SLASHWORK_BASE_URL, then https://slashwork.sh. Must be https (http only for localhost dev).

/work init (one-time setup)

One step: authenticate. Run Step init-1 and relay its AUTH: lines.

Step init-1: authenticate

Read the full file on GitHub · 258 lines

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.

2mo ago First seen · 258 lines · 232 tokens per session scan C 9042f75b7c93

Subscribe to this mod's changes

work is a skill published in the GitHub repository slashwork-sh/plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 232 tokens to every session and 3,411 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

work next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
workslashwork-sh/plugin	Skill	1	1mo ago	MIT	C	232	Claude Code
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	316k	7d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

work