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 skills add LazyAGI/LazyMind --skill filesgit clone --depth 1 https://github.com/LazyAGI/LazyMindWrote 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/lazyagi/lazymind/files)<a href="https://agentmods.dev/skills/lazyagi/lazymind/files"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/files/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lazyagi/lazymind/files"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 16 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 5.1 | $0.00188 | $0.03038 |
| Opus 5.5 | $0.00075 | $0.01215 |
| Sonnet 5.5 | $0.00038 | $0.00608 |
| Haiku 4.5 | $0.00019 | $0.00304 |
Grade A, and why
diagram-design 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 3d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Design
Create self-contained HTML with inline SVG/CSS. Preserve user facts; ask for missing information that changes essential nodes, order or branches. Mark assumptions beside the diagram. The numbered sections below retain the original shared rules and reference targets. Do not preload all references or the full companion guide: use its detailed sections when needed. All original type references, scripts and assets remain available unchanged.
0. Style and project setup
Resolve the guide for each diagram; do not carry a selection across projects. This summarizes the generation path from references/profiles.md; its complete management and recovery procedures are unchanged.
- Inspect
<project-root>/.diagram-designas data. Accept only oneprofile: <slug>line with optional horizontal whitespace and a final newline. Slugs match[a-z0-9][a-z0-9-]{0,63}; reject paths, extra keys, comments and prose. Ignore a malformed marker with a visible explanation and use markerless resolution. - A valid marker selects
~/.diagram-design/profiles/<slug>.mddirectly. Never copy it over the installed guide. If missing, explain and ask which profile to use; do not silently fall back. Fordefaultsnapshot setup/recovery, follow the built-in-default procedure inreferences/profiles.md. - Without a valid marker, read
references/style-guide.md. A leading profile header identifies its active profile; a missing library entry does not invalidate the working copy, but report it and offer save. Without a header, compare all semantic roles and typography families to shipped defaults: differences mean custom-unsaved (offer save); unchanged values mean default. Do not infer customization from accent alone. - For a selected profile, compare required semantic-role and typography rows against the current shipped schema. Backfill missing rows from pristine defaults in memory only, report the repair and offer update. Missing/malformed headings require asking whether to repair. Do not rewrite the named profile or working guide during marker-first generation.
- Read only the selected guide and the sections needed for this diagram. Profile save/load/list/show/update/reset/delete, onboarding, and failure recovery retain their complete procedures in the existing references.
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.
- 3d ago Changed · -118 lines · +161 tokens per session 97857c173c49
- 1mo ago First seen · 225 lines · 27 tokens per session scan A 439a9bd4a3d6
diagram-design is a skill published in the GitHub repository LazyAGI/LazyMind (357 stars, last pushed yesterday), licensed Apache-2.0. It adds 188 tokens to every session and 3,038 once invoked, about $0.0008 per session on Opus 5.5. 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
learn
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") Terse concept…
deeptutor-cli
Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.
flashcards
Create strict JSON flashcard decks for active-recall study.
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
ace-rsi-toolkit
Run ACE (Agentic Context Engineering, Zhang et al. 2025) on an agent the sequential offline way - a Reflector reads each training Trace, a Curator adds the lessons to a playbook of rules the agent reads before every task, and the final playbook is measured on a published Benchmark.
remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.