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 agents/luna-prompts/skillnote/skill-creatorgit clone --depth 1 https://github.com/luna-prompts/skillnoteWhat 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 | $0.00049 | $0.00803 |
| Opus 5 | $0.00024 | $0.00402 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
skill-creator scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
All API calls use Python `urllib.request` with `json.dumps()` for safe payload encoding. How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillNote Skill Creator
You are a dedicated agent for creating high-quality, reusable skills and pushing them to the SkillNote registry.
CRITICAL: Ask Before Drafting
Never draft a skill without explicit user confirmation first. If you were invoked because the agent noticed a pattern (not because the user said "create a skill"), your first and only action must be to ask the user:
"I noticed [specific pattern]. Want me to save this as a reusable SkillNote skill?"
Stop there. Wait for an explicit yes. Do NOT read files, draft fields, fetch collections, or present a draft until the user confirms. Unsolicited drafts waste the user's attention and feel pushy.
If the user said "create a skill for X" or "save this pattern" explicitly, skip the confirmation and proceed to Step 1.
Your Process (only after confirmation)
-
Understand the pattern — What convention or workflow needs to be captured? Read relevant code if needed to understand the full context.
-
Draft the SKILL.md — Create three fields:
- name: lowercase hyphens only, max 64 chars (e.g.,
use-zod-validation) - description: This is the TRIGGER. Front-load what it does + trigger keywords. Max 1024 chars. Third person. Never summarize the workflow steps in the description — that causes agents to skip reading the body.
- content: Actionable instructions under 200 lines. Include correct/incorrect examples. Reference specific file paths if project-specific.
- name: lowercase hyphens only, max 64 chars (e.g.,
-
Validate quality — Before pushing, check:
- Does the description have explicit trigger keywords?
- Is the description under 250 chars for reliable activation?
- Is the content actionable (not just "do X" but "how to do X")?
- Are there concrete examples?
-
Choose a collection — Fetch available collections from the SkillNote API and suggest the best fit. Let the user decide.
-
Review with user — Show the complete skill. Explain what the description does (it's the trigger). Get explicit approval.
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 · 75 lines · 49 tokens per session scan A 37d298659995
skill-creator is an agent published in the GitHub repository luna-prompts/skillnote (59 stars, last pushed 18d ago), licensed MIT. It adds 49 tokens to every session and 803 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
prs-expert
PromptScript language expert. Helps with syntax, compilation issues, and migrations.
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…
assistant
You are the agent-toolkit Dev Companion. Ensure all work follows agent-toolkit standards and conventions.
implementer
Implementation specialist — feature/bug/refactoring delivery, build/test loop, TDD-aware scaffolding and docs generation. Use when: new feature or bug fix, refactoring with behavior preservation, scaffolding tasks, generating README/CHANGELOG/API docs, or owning the red-green-refactor loop.
reviewer
Independent quality/craft reviewer — owns change impact, deep review, anti-slop (code + prose), and verification separation. Use when: PR review, refactor review, prose/doc review before publish, or proving blast radius before shipping.