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/mayank-io/mstack/check-namenpx skills add mayank-io/mstack --skill check-namegit clone --depth 1 https://github.com/mayank-io/mstackWhat 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 | $0.00066 | $0.01335 |
| Opus 5 | $0.00033 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade B, and why
check-name scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls "$HOME/.claude/skills/gstack/browse/dist/browse" && echo READY || echo MISSING How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Name Availability
Run an aggregated availability sweep on a candidate company name across three sources and produce a single markdown report. The report drives a real filing decision — accuracy over speed.
When to invoke
The user asks any of:
- "Is
<name>available?" - "Can I file
<name>as an LLC?" - "Check trademark on
<name>" - "Is
<name>.comtaken?" - "Run availability checks on
<name>" - "Clear
<name>for me"
Arguments
Parse from $ARGUMENTS:
- Candidate name (positional, required) — the bare candidate. Can be one or more words. Quote if it contains spaces.
--systems <csv>(optional) — subset ofuspto,wa-sos,domain. Default: all three.--class <csv>(optional) — USPTO class filter, e.g.35,42. Default: pick from business context (see below).--json(optional) — emit machine-readable JSON instead of markdown.--refresh(optional) — bypass cache.
If the candidate name is missing or ambiguous, ask the user before invoking.
Picking USPTO classes (do this before running)
The user usually doesn't know Nice Classification — pick the classes for them, announce, run.
Procedure:
- If
--classwas explicitly provided, use it verbatim. No question. - Otherwise, infer the business archetype. Check the recent conversation for cues:
- "fractional CTO firm", "tech consulting", "advisory" → IT consulting archetype
- "SaaS", "platform", "app" → SaaS archetype
- "store", "DTC", "brand" → e-commerce archetype
- "restaurant", "café", "bar" → food service archetype
- "coaching", "training", "course" → education archetype
- (etc.)
- Look up the matching class set in
${CLAUDE_PLUGIN_ROOT}/playbooks/uspto-nice-classes.md(the "Business archetype → class map" table is the lookup). - Announce the choice in ONE LINE before running. Example:
Searching USPTO classes 35 (business consulting) and 42 (IT consulting) — standard for a fractional CTO firm. Override with
/check-name <name> --class X,Yif you want different scope. - If you can't infer the archetype from context AND the user hasn't told you, ask ONCE with
AskUserQuestion. The options should be drawn from the archetype map. Don't dump the full 45-class taxonomy — give 4 archetypes max plus "Other (describe)". - Run with the picked
--class.
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 · 103 lines · 66 tokens per session scan B 8412246838e3
check-name is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 1,335 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…