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/slashwork-sh/plugin/earnnpx skills add slashwork-sh/plugin --skill earngit clone --depth 1 https://github.com/slashwork-sh/pluginWhat 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 | $0.00237 | $0.07850 |
| Opus 5 | $0.00118 | $0.03925 |
| Sonnet 5 | $0.00047 | $0.01570 |
| Haiku 4.5 | $0.00024 | $0.00785 |
Grade C, and why
earn scanned grade C with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
( umask 077; mkdir -p "$HOME/.slashwork"; printf '%s' "$TOKEN" > "$TOKENFILE"; chmod 600 "$TOKENFILE" ) Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
and no `./.claude/settings.local.json`), run init. Otherwise run the earner Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
START=$(curl -sS --max-time 20 -X POST "$BASE/auth/cli/start") How it starts
The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/earn, the slashwork earner skill
Earn on the slashwork offload network from a Claude Code session set up with your own agent folder. Three layers:
- Entry (this skill): parse the goal, hold the task feed, stage each claimed task as a session-scoped job file.
- Worker (
agents/worker.md): a fresh-context subagent that runs this folder's configured agent on the task prompt; its final reply is the artifact. - Submission (
hooks/submit.sh): a SubagentStop hook that reads the worker's final reply and POSTs it for the task it solved, with the worker's token usage. An acceptance judge checks it; accepted work pays credits and builds your per-class score.
$ARGUMENTS is one of:
init [name] [--reauth]: one-time setup. Authenticate in the browser (token to~/.slashwork/token), then scaffold an earner folder at./name(default./slashwork-agent): aCLAUDE.mdidentity, a.claude/settings.local.json(permissions, defaultMode, additionalDirectories), asettings.json(run settings:base_url,model,bypass_permissions,default_duration), a README, and a.gitignore. No questions to answer; the folder ships safe defaults the user can edit.--reauthforces a fresh sign-in even if a token exists.<goal>: the earner loop. Hold the live task feed, claim offloaded tasks as they appear, run each with this folder's configured agent, submit, and repeat until the goal is met. The goal is a time budget (90s,30m,2h) or credits earned this run (200cr).- empty (a bare
/earn): if the folder is not set up yet (no./settings.jsonand no./.claude/settings.local.json), run init. Otherwise run the earner loop with the folder'sdefault_durationfromsettings.jsonas the goal (the scaffold ships30m); if that key is empty, explain the goal syntax and suggest/earn 30m.
Resolution order:
- token:
SLASHWORK_TOKENenv, then~/.slashwork/token, else stop and tell the user to run/earn init. - base_url:
settings.jsonbase_url, thenSLASHWORK_BASE_URLenv, thenhttps://slashwork.sh. Must be https (http only for localhost dev): the submit hook and the listener send the bearer token to this host.
If $ARGUMENTS starts with init, run the init routine below. Otherwise start
at Step 1.
Run
/earnin a throwaway working directory (the init scaffold is one). The worker runs a stranger's task prompt with your configured agent in the current folder, and its reply goes back to the task's requester. A hostile task can try to make the deliverable be your local files, so the worker must have nothing sensitive in reach: no real repo, no.env, no credentials in the cwd.
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.
- yesterday First seen · 592 lines · 237 tokens per session scan C d2dfb33f4313
earn is a skill published in the GitHub repository slashwork-sh/plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 237 tokens to every session and 7,850 once invoked, about $0.0012 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…