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/thermiteau/maverick/do-upskillnpx skills add thermiteau/maverick --skill do-upskillgit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/thermiteau/maverick/do-upskill)<a href="https://agentmods.dev/skills/thermiteau/maverick/do-upskill"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/do-upskill.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 | $0.00044 | $0.04471 |
| Opus 5 | $0.00022 | $0.02235 |
| Sonnet 5 | $0.00009 | $0.00894 |
| Haiku 4.5 | $0.00004 | $0.00447 |
Grade A, and why
do-upskill 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 4d 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Project Skills
Scan the current project's codebase for a given topic and produce a project-specific skill file at docs/maverick/skills/<topic>/SKILL.md.
Primary audience: LLMs. The generated skill is project implementation and usage guidance — what technology is used, how it's configured, and where the code lives. It is NOT best practices (the maverick best-practice skill handles that). Keep it dense, factual, and under 100 lines.
Preflight (mandatory)
Run this first. If it exits non-zero, halt and report the stderr output to the user verbatim. Do not proceed.
uv run maverick preflight do-upskill
The check verifies the project is initialised and uv is on PATH.
Invocation
Topics live in ${CLAUDE_PLUGIN_ROOT}/skills/do-upskill/topics.json
(resolve the env var once via Bash — the runtime cwd is the target
project, not the plugin).
$ARGUMENTSnames a topic (e.g.logging): process exactly that one topic and stop. This is the mode other skills and mid-task lookups use — never expand a single-topic request into a full scan.- No arguments: process all topics in the JSON array without prompting the user. Do not present a list of choices.
For each topic entry being processed:
- Read the
topic,prompt,bestPracticeSkill, andscanHintsfields - If the best-practice skill file exists, read it for reference
- Detect repository type (once, cached across all topics — see step 0 below)
- Single-repo: scan the entire repo, write to
docs/maverick/skills/<topic>/SKILL.md - Mono-repo: for each package, scope scanning to that package directory and write to
<package>/docs/maverick/skills/<topic>/SKILL.md. Also scan the repo root for cross-cutting implementations and write those todocs/maverick/skills/<topic>/SKILL.md. Cross-cutting topics (see below) always write to root only.
Use subagents or parallel agents to process multiple topics concurrently when possible.
Input
Each topic entry in topics.json provides:
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.
- 4d ago First seen · 405 lines · 44 tokens per session scan A 806ac41076e8
do-upskill is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 4,471 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 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…