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/xcaeser/work-skill/work-helpnpx skills add xcaeser/work-skill --skill work-helpgit clone --depth 1 https://github.com/xcaeser/work-skillWhat 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 | $0.00035 | $0.00861 |
| Opus 5 | $0.00017 | $0.00430 |
| Sonnet 5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
work-help 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 2d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work / 11. Help
Show the Work skill family directly. Do not inspect the repository, spawn agents, create goals, or run a task. Do not make the user remember subcommands.
When explaining the shared standard, use the $work-quality description below;
do not resolve or read files outside this skill folder.
Work skills
| Skill | Use it for |
|---|---|
$work |
Delegate and integrate a free-form implementation task |
1. $work-init |
Start and verify a new project |
2. $work-ideate |
Brainstorm with a rigorous, question-by-question creative sparring partner |
3. $work-plan |
Build a detailed read-only plan with Sol xhigh |
4. $work-test |
Inspect real behavior, add justified tests, and report omissions and bugs |
5. $work-concern |
Surface evidence-backed concerns in the current implementation without editing |
6. $work-checklist |
Capture conversation as a checklist, then optionally execute it |
7. $work-audit |
Audit risks with Sol xhigh and produce an executor-ready fix plan |
8. $work-clean |
Analyze code smells with Sol xhigh and produce an executor-ready cleanup plan |
9. $work-quality |
Pass the Work golden rules directly into the conversation |
10. $work-status |
Show the current goal, agents, evidence, and next action |
11. $work-help |
Show this map |
Model shorthand
Work / 2. Ideate: interactive conversation; no agents or model selection.Work / 4. Test: parent-led test implementation; no agents or coverage target.Work / 5. Concern: lightweight read-only inspection; no agents or fix plan.Work / 6. Checklist: Capture returns a checklist only; Execute registers one parent-owned goal. No agents.Work / 3. Plan,7. Audit, and8. Clean: one read-only Sol xhigh analyst; no edits.- Plans are executor-agnostic and detailed enough for a lower-capability model with no hidden context.
- Terra Low handles small mechanical chores; Terra Medium handles structured exploration or extraction.
mixlets the parent choose Sol or Terra per assignment and explain the split before launch.- Executors use
fork_turns: none, narrow ownership, and compact artifact-first handoffs to control token use. $work: automatic routing (Sol Low for ordinary work) unless the user proposes a count, profile, or effort. Advanced form:$work [N] [sol|terra|mix] [effort] <task>. Work explains its recommendation and waits for confirmation; it never invents assignments to satisfy an oversized count.
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.
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.
- 2d ago First seen · 56 lines · 35 tokens per session scan A 6b0b7097be46
work-help is a skill published in the GitHub repository xcaeser/work-skill (2 stars, last pushed 21d ago), licensed MIT. It adds 35 tokens to every session and 861 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
changes-report
Report all repository changes that entered a target branch during one required date or period, grouped by product change and written as plain English for a broad audience. Use for daily, weekly, date-range, or relative-period change summaries rather than explaining one known diff.
jira-issue-create
Create one or more Jira issues through acli from user-approved drafts using heading-based Context, Acceptance criteria, and Engineering notes sections. Use only when explicitly invoked to create Jira issues; use jira-issue-refine when requirements still need refinement.
claude-review
Run an independent Claude Opus review of the complete current change against the repository's default branch, then verify its findings locally. Use after focused checks pass when you want a second model to review the change before further edits or delivery.
test-gap-review
Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.
orcast
Use when orchestrating multiple agents in Orca: fan out parallel workers, pipeline work across stages, adversarially verify findings, run judge panels or loop-until-dry sweeps, or delegate a task and get the result back. You write a Plan definition in real JavaScript — a worker-workflow graph of worker, action, and…
jira-issue-deliver
Autonomously deliver one Jira issue from intake to a ready GitHub pull request. Use only when the user authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback.