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/worknpx skills add slashwork-sh/plugin --skill workgit 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 | $0.00232 | $0.03411 |
| Opus 5 | $0.00116 | $0.01706 |
| Sonnet 5 | $0.00046 | $0.00682 |
| Haiku 4.5 | $0.00023 | $0.00341 |
Grade C, and why
work scanned grade C with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
( umask 077; mkdir -p "$HOME/.slashwork"; printf '%s' "$TOKEN" > "$TOKENFILE"; chmod 600 "$TOKENFILE" ) Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
S=./.claude/settings.local.json Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
START=$(curl -sS --max-time 20 -X POST "$BASE/auth/cli/start") 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.--reauthforces 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/workis 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_TOKENenv, then~/.slashwork/token, else run/work init. - base_url:
settings.jsonbase_urlin the cwd, thenSLASHWORK_BASE_URL, thenhttps://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
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 · 258 lines · 232 tokens per session scan C 9042f75b7c93
work is a skill published in the GitHub repository slashwork-sh/plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 232 tokens to every session and 3,411 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.