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 commands/devolutions/avalonia-extensions/worksetupgit clone --depth 1 https://github.com/Devolutions/avalonia-extensionsWhat 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 | $0.00712 |
| Opus 5 | $0.00017 | $0.00356 |
| Sonnet 5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
worksetup 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.
What it actually says
Configure SampleApp startup defaults for development.
Arguments:
- theme (required):
MacOS,MacOSClassic/Classic/MacClassic,MacOSLiquidGlass/LiquidGlass/Liquid/Glass,DevExpress,Linux, orDefault - pageTitle (optional, default
Overview): page title to select at startup - scale (optional, default
Default):Default,100%,125%,150%,175%,200%,225%,250%,275%,300%,400% - projectPlan (optional): planning doc name/partial name under
.claude/docs/planning
1) Parse and validate inputs
-
Parse
/worksetup [theme] [pageTitle] [scale] [projectPlan] -
Validate theme and scale against allowed values
-
Theme matching is case-insensitive and accepts aliases listed above
2) Update startup settings in
samples/SampleApp/PageCatalog/page-catalog.jsoncEdit only the
sampleAppStartUpSettingsblock:"sampleAppStartUpSettings": { "theme": "DevExpress", "selectedPage": "ComboBox", "scale": "default" }theme: set from the validated theme argumentselectedPage: set from resolved page title (see Step 3)scale: set from validated scale argument (if provided), otherwise preserve existing value
The app applies these settings at runtime; do not edit
App.axamlorMainWindowViewModel.csfor normal/worksetupusage.3) Resolve page title
Collect candidate page titles from:
samples/SampleApp/PageCatalog/page-catalog.jsonc->pages.*[].uniqueTitle
Match rules:
-
case-insensitive
-
prefer exact match
-
then partial match
-
if ambiguous, ask user to clarify
4) Scale value format
In
sampleAppStartUpSettings.scale, write one of:default100%,125%,150%,175%,200%,225%,250%,275%,300%,400%
5) Error handling
- Invalid theme: report valid theme options
- Invalid scale: report valid scale options
- No page match: list available page titles from catalog
- Ambiguous page match: ask user to be more specific
6) Completion message
Report:
- selected theme
- selected startup page
- selected startup scale (if changed)
- files edited
Do not run the app unless explicitly asked.
7) Optional planning doc handling
If projectPlan is provided (or an open planning doc is detected):
- locate matching file in
.claude/docs/planning/**/*.md - load and summarize current phase + next steps
- ask whether to proceed with the plan work
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 · 70 lines · 35 tokens per session scan A 674df4442e70
worksetup is a command published in the GitHub repository Devolutions/avalonia-extensions (79 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 712 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.