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 bitjaru/styleseed --skill ss-learngit clone --depth 1 https://github.com/bitjaru/styleseedWrote 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/bitjaru/styleseed/ss-learn)<a href="https://agentmods.dev/skills/bitjaru/styleseed/ss-learn"><img src="https://agentmods.dev/badge/skills/bitjaru/styleseed/ss-learn/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/bitjaru/styleseed/ss-learn"><img src="https://agentmods.dev/badge/skills/bitjaru/styleseed/ss-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00073 | $0.01102 |
| Opus 5.5 | $0.00029 | $0.00441 |
| Sonnet 5.5 | $0.00015 | $0.00220 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
ss-learn 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn from project design decisions
ss-learn turns a specific human-approved correction into a generalized candidate rule. It
does not train a model, scrape a repository, or upload telemetry. The CLI is local-only. An
optional plugin MCP bridge can expose one exact package to its connected client/model only after a
separate one-time human grant.
Read references/privacy-contract.md before using this skill.
When not to use
- The user did not explicitly ask to capture or share a lesson.
- The change was accepted only by the agent, not a person.
- The lesson cannot be expressed without client/product identity, source code, a screenshot, proprietary tokens, or user content.
- A score or visual pass was not actually measured. Record it as
nullornot-run; never infer. - The observation belongs only to one project's taste. Keep it in
STYLESEED.mdinstead.
1. Initialize local learning
After explicit user approval:
node <installed-ss-learn>/scripts/learning.mjs init --project-root .
This creates .styleseed/learning/config.json with sharing disabled and all raw-material
collection disabled. It performs no network request.
2. Draft a candidate
Use references/candidate.schema.json. Generalize the lesson:
- problem: what design failure was observed;
- intervention: what bounded change the person accepted;
- rationale: why it improved the product job;
- appliesWhen: conditions where the judgment should transfer;
- avoidWhen: counterexamples and failure boundaries;
- evidence: only measured scores, verification status, and optional SHA-256 artifact hashes.
Do not include project names, URLs, paths, emails, source snippets, prompts, screenshots, colors, font names, or component names. Then capture it:
node <installed-ss-learn>/scripts/learning.mjs capture \
--project-root . \
--input /path/to/candidate.json
The CLI validates maintained context IDs, exact fields, privacy patterns, and evidence honesty.
It writes an immutable draft ID under .styleseed/learning/candidates/.
What ships with it
10 files 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.
- agents/openai.yaml 291 B
- references/candidate-record.schema.json 2.1 KB
- references/candidate.schema.json 2.4 KB
- references/privacy-contract.md 2.1 KB
- references/share-package.schema.json 808 B
- scripts/learning-contract.mjs 9.6 KB runs code
- scripts/learning-package.mjs 4.1 KB runs code
- scripts/learning.mjs 10 KB runs code
- scripts/privacy-scan.mjs 3.1 KB runs code
- scripts/secure-fs.mjs 11 KB runs code
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.
- 1mo ago First seen · 126 lines · 73 tokens per session scan A 689f7eb21888
ss-learn is a skill published in the GitHub repository bitjaru/styleseed (979 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 1,102 once invoked, about $0.0003 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
s2-docs
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField…
onboarding
Onboarding guide for a designer or engineer joining a team that uses the design system, grounded in the repo and Figma library rather than a template. Triggers: onboard a new designer, onboard a new engineer, getting-started guide, first week with the system, developer or designer onboarding.
sigil-migration
Before migrating, audit the existing project.
sigil-component
Every Sigil component lives in packages/components/src/ and follows this pattern.
design-to-code
Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.
seed-design
An integration guide for SEED Design, covering shared component specifications and foundations plus React and Lynx implementation guidance.