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-checklistnpx skills add xcaeser/work-skill --skill work-checklistgit clone --depth 1 https://github.com/xcaeser/work-skillWrote 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.
[](https://agentmods.dev/skills/xcaeser/work-skill/work-checklist)<a href="https://agentmods.dev/skills/xcaeser/work-skill/work-checklist"><img src="https://agentmods.dev/badge/skills/xcaeser/work-skill/work-checklist.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00077 | $0.01593 |
| Opus 5 | $0.00039 | $0.00796 |
| Sonnet 5 | $0.00015 | $0.00319 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
work-checklist 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 3d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work / 6. Checklist
Turn conversation into accountable next steps. Preserve reliability, meaningful testing, simplicity, user state, and clean breaks. Do not flatten an idea into a defect list or invent work to make the checklist look complete.
Use the strongest current source, in this order:
- The user's latest explicit decisions and constraints.
- A
$work-ideatedecision,$work-planoutput, or named requirements. - A
$work-concernor$work-auditresult. - The smallest coherent outcome supported by the current conversation.
Preserve open questions as open questions. Distinguish evidence, assumptions, preferences, commitments, and rejected directions.
Choose the mode
- Capture: When the user asks to make, save, organize, or turn the conversation into a checklist without asking for execution, return the checklist only. Do not create a goal, inspect unrelated files, or edit anything.
- Execute: When the user asks to implement, do, resolve, go through, or complete the checklist, register one goal and work every item.
If intent is ambiguous, default to Capture and end with the exact command or sentence that would start execution. Do not silently turn planning into implementation.
Do not spawn agents. The parent owns verification, edits, integration, and proof. If execution genuinely requires orchestration, preserve the approved checklist and hand it unchanged to $work.
Build the checklist
Merge duplicates and order items by dependency first, then user value and risk. Use one of these types:
deliverable: something that must exist or change;decision: a choice that must be resolved;experiment: evidence needed before committing to a direction;guardrail: a boundary or non-goal that must remain true;concern: a suspected implementation problem to verify and resolve or disprove.
Keep Capture mode to at most 10 items unless the user explicitly asks for an
exhaustive breakdown. Every item must trace directly to the conversation. Do
not invent architecture, screens, features, edge cases, research sample sizes,
success thresholds, or implementation chores. If a necessary detail is
unknown, create one decision item instead of choosing it for the user.
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.
- 3d ago First seen · 136 lines · 77 tokens per session scan A 9e16d83b7319
work-checklist is a skill published in the GitHub repository xcaeser/work-skill (2 stars, last pushed 23d ago), licensed MIT. It adds 77 tokens to every session and 1,593 once invoked, about $0.0004 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.