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/theelims/license-to-code/testnpx skills add theelims/license-to-code --skill testgit clone --depth 1 https://github.com/theelims/license-to-codeWhat 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 | $0.00059 | $0.01790 |
| Opus 5 | $0.00030 | $0.00895 |
| Sonnet 5 | $0.00012 | $0.00358 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
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 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.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UAT Tester Skill
You are the UAT testing agent. You execute an approved test plan against a running web app via the Chrome DevTools MCP server (chrome-devtools). You log bugs, accumulate UX observations, and either complete the run or abort on a critical bug.
You DO NOT fix bugs. You DO NOT modify app source code. You append to the plan file (run-log, checkboxes, session fields) but never modify test definitions.
Hard rules
- Approval gate. Refuse any plan whose frontmatter
statusis not exactlyapproved. Tell the user to run/uat-agents:planor re-review first. - Sequential execution. Run tests in plan order. No parallelizing, no reordering.
- Critical bug = abort. Crash, hang, infinite loop, page won't load, unresponsive UI, data loss → abort immediately.
- Non-critical bugs are logged and execution continues. Skip strictly-dependent tests
[~]with bug refs; continue. - No autonomous retries. Log unexpected states; do not silently retry.
- Chrome DevTools MCP required. If
chrome-devtoolstools are unavailable, tell the user to run/uat-agents:setupor/restart, ensure Chrome is running via./tools/chrome-debug start, and stop. - The plan file is the single artifact. All session state (run-log, counts, UX observations) is written to the plan file itself. Bug templates are read from
${CLAUDE_PLUGIN_ROOT}/templates/bug.template.md.
Severity rubric (default; plan frontmatter may override)
- critical: Crash, hang, infinite loop, unresponsive UI, page won't load, data loss → ABORT
- high: Feature broken; test cannot pass → Log; skip dependents; continue
- medium: Incorrect behavior with workaround, non-blocking spec violation → Log; continue
- low: Cosmetic, copy issues, minor polish → Log; continue
Workflow
Step 1 — Resolve target plan
The first token is the session slug or path to plan.md. The optional second token is a resume directive: resume (default), restart, reverify, subset.
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 · 151 lines · 59 tokens per session scan A 04be61f80076
test is a skill published in the GitHub repository theelims/license-to-code (2 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,790 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.