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 skills add xcaeser/work-skill --skill work-testgit 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-test)<a href="https://agentmods.dev/skills/xcaeser/work-skill/work-test"><img src="https://agentmods.dev/badge/skills/xcaeser/work-skill/work-test/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.
<a href="https://agentmods.dev/skills/xcaeser/work-skill/work-test"><img src="https://agentmods.dev/badge/skills/xcaeser/work-skill/work-test.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.00932 |
| Opus 5.5 | $0.00020 | $0.00373 |
| Sonnet 5.5 | $0.00010 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
work-test 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work / 4. Test
Write meaningful tests for behavior the product genuinely promises or currently depends on. The testing rules below are binding.
Work directly in the parent conversation. Do not spawn agents or register a goal unless the user explicitly asks. Testing is implementation work: inspect first, show the plan, make the smallest justified edits, run the tests, and report the evidence.
Inspect before writing
Read the applicable project instructions, repository status and diff, implementation, existing tests and helpers, public APIs, consumers, and actual user flows. Identify the behavior users or current callers rely on. Do not invent requirements, hypothetical threats, or unrealistic edge cases.
If the user did not name a target, choose the smallest coherent feature or current change that can be understood and tested safely. State the scope. If no meaningful behavior is worth testing, stop and explain why; never add a test only to increase coverage.
Publish the test plan
Before editing, provide one entry per justified behavior in this exact format:
- Behavior being protected
- Why it matters
- Test level: unit, integration, or end-to-end
- Exact observable assertion
Keep the plan short. Prefer a small number of high-value tests in this order:
- Core happy paths.
- Realistic failure paths.
- Important boundaries.
- Previously broken behavior.
- Data persistence, permissions, billing, authentication, or destructive actions when relevant.
Select meaningful tests
- Test observable behavior, not internal implementation details.
- Test negative behavior only when a real contract or regression needs protection.
- Prefer integration tests for interactions between modules owned by the project.
- Mock external boundaries only when necessary: network APIs, time, randomness, queues, email, payment providers, or databases.
- Use realistic inputs and fixtures. Keep tests deterministic and independent of execution order.
- Assert the actual result, persisted state, returned error, emitted event, or externally visible side effect.
- Keep each test focused on one behavior without splitting a simple workflow into redundant cases.
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.
- 1mo ago First seen · 84 lines · 49 tokens per session scan A d21fb54c937f
work-test is a skill published in the GitHub repository xcaeser/work-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 932 once invoked, about $0.0002 per session on Opus 5.5. 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
cli-control
Verify terminal-hosted CLI or TUI behavior with repeatable local evidence. Use for output, prompts, interactive input, signals, hangs, resizing, startup, exit status, or terminal restoration; not for browser, desktop, or Electron interfaces, which belong to ui-control.
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.
bug-report-reproduce
Reproduce a user, customer, or support-reported problem with synthetic data, prove the cause with a temporary test, record a narrated click-through walkthrough of the symptom, and report what was and was not proven. Use when the user links a bug report, support thread, or ticket and asks to reproduce it, find the…
crap-index-assess
Assess method-level change risk with the Change Risk Anti-Patterns (CRAP) index and recommend focused testing or complexity reduction. Use when the user asks what CRAP means or how to calculate, interpret, or reduce a CRAP score, or when the repository's configured CRAP check covers changed methods; not as a general…
test-design
Design or write reproducible tests matched to behavioral risk before implementation. Use for product behavior; for tooling or infrastructure, use it only when native checks such as linters, validators, dry runs, or plans cannot show the behavior.
behavior-implement
Implement one observable behavior or bug fix with red-green-refactor, writing a focused test that fails first, the minimum code that passes it, and then a behavior-preserving cleanup. Use for product behavior changes; for tooling or infrastructure, use it only when native checks such as linters, validators, dry runs…