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/xcrft/mastermind/mastermind-component-researchnpx skills add xcrft/mastermind --skill mastermind-component-researchgit clone --depth 1 https://github.com/xcrft/mastermindWrote 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/xcrft/mastermind/mastermind-component-research)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-component-research"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-component-research.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 | $0.00073 | $0.00982 |
| Opus 5 | $0.00036 | $0.00491 |
| Sonnet 5 | $0.00015 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
mastermind-component-research 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind component research
The default failure of an agent writing UI is not bad markup. It is writing a component that already exists, or changing a props contract without seeing who depends on it. Both are structural questions, and the codegraph answers them.
Answer these before writing. Evidence is a query result, not a recollection.
Does it already exist?
mmcg_search "Button" # exact name
mmcg_files --prefix src/components # what the component directory holds
mmcg_centrality --prefix src/components # the components everything already leans on
Search the name you were about to invent, then the words around it. A Button
may live as BaseButton, AppButton, or UiButton, and a design system rarely
names things the way a ticket does. mmcg_centrality is the fastest read of a
component library you do not know: the highest in-degree symbols are what the
codebase actually builds on.
Report the search as evidence — the names tried and what came back. "I looked and found nothing" without the queries is not a finding, and reinvention is the most expensive mistake available here.
Who renders it?
mmcg_callers "Button" # components that render it
mmcg_impact "Button" --depth 3 # transitive blast radius
mmcg_imported_by "Button" # files importing it, including barrels
mmcg_callers answers "who renders this": JSX usage (<Button />) and Vue
template usage (<base-button />) are call edges from the containing component.
A component with callers is a shared contract — treat a change to it as a change
to every caller, and say how many there are.
Zero callers means one of three things, and they are not the same: the component
is new, it is dead, or it is reached in a way the graph cannot see. Check the
invisible paths before concluding it is dead — route tables, lazy import(),
story and test files, and Vue components auto-imported by build tooling never
produce an edge.
What is the contract?
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 · 97 lines · 73 tokens per session scan A 82c32b5baaaf
mastermind-component-research is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 982 once invoked, about $0.0004 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
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
frontend-design
做有辨识度、生产级、高设计质量的前端界面。当用户要构建网页组件、页面、海报或应用(网站、落地页、仪表盘、React 组件、HTML/CSS 布局,或美化任何 Web UI)时使用。产出有创意、精致、避免千篇一律 AI 风格的代码与界面。.
pi-tui-design
Create distinctive, crafted TUI components for pi using @earendil-works/pi-tui and @earendil-works/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…
orchestrate
Tree-aware multi-agent GitHub-issue pool. Conductor manages task-tree from task-splitting-evaluation, executing depth-first per branch while parallelizing roots/orphans. Each worker agent owns its subtree lifecycle. Conductor tracks state (pending/started/in-progress/completed/halted) in GitHub +…
bonsai-ninja
Use bonsai-ninja as compiler-backed structural evidence when mapping a codebase, finding symbols, tracing behavior, inspecting dataflow, debugging across files, reviewing change impact, exporting graph facts, or running SAST.
task-splitting-evaluation
Recursive pre-implementation GitHub task splitting and evaluation flow. Use when the user wants Claude agents to evaluate unhandled tasks, skip already-processed tasks, mark easy leaves with detailed executor-ready comments, split broad tasks into GitHub subtasks, and keep recursing until every leaf is well described…