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 kensaurus/cursor-kenji --skill meta-skill-creatorgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/meta-skill-creator)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/meta-skill-creator"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/meta-skill-creator/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/kensaurus/cursor-kenji/meta-skill-creator"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/meta-skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Rogue Agent · line 214 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 253 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00056 | $0.03032 |
| Opus 5 | $0.00028 | $0.01516 |
| Sonnet 5 | $0.00011 | $0.00606 |
| Haiku 4.5 | $0.00006 | $0.00303 |
Grade A, and why
meta-skill-creator 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 5d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Degree of freedom: MIXED. Authoring judgment is [HIGH freedom];
house limits, frontmatter shape, and the T1–T6 checklist are
[LOW freedom — do not skip].
Guidance for creating effective skills.
About Skills
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
What Skills Provide
- Specialized workflows - Multi-step procedures for specific domains
- Tool integrations - working with specific file formats or APIs
- Domain expertise - Company-specific knowledge, schemas, business logic
- Bundled resources - Scripts, references, and assets for complex and repetitive tasks
Core Principles
Concise is Key
The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"
Prefer concise examples over verbose explanations.
Pruning — the verbosity levers
Every line must earn its tokens. Sweep each skill with these tests (adapted from mattpocock/skills, MIT):
- No-op test. Does the line change behavior versus what the agent already does by default? "Be thorough" is a no-op; delete the whole sentence, don't trim words from it. A weak intensifier is cured by a stronger word (relentless), not more prose.
- Positive phrasing. Steering by prohibition backfires — "don't think of an elephant" names the elephant. State the target behavior so the banned one is never spoken; keep a prohibition only as a hard guardrail you can't phrase positively, paired with what to do instead.
- Leading words. Replace a restated quality with one compact concept the model already knows — "fast, deterministic, low-overhead" collapses to a tight loop. Fewer tokens and a sharper hook for the agent's thinking.
- Single source of truth. Each meaning lives in exactly one place; a duplicated rule costs maintenance, tokens, and inflates its apparent importance.
- One trigger per branch. In descriptions, synonyms that rename the same trigger are duplication — collapse them; keep only genuinely distinct branches.
- Checkable completion criteria. End each step on a condition the agent can verify ("every modified file accounted for"), not a vibe ("make sure it's good") — vague criteria invite premature completion.
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.
- 5d ago First seen · 290 lines · 56 tokens per session scan A 46dc1bda7c44
meta-skill-creator is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 10d ago), licensed MIT. It adds 56 tokens to every session and 3,032 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
comprehensive-enrichment
Enrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.
paid-channel-prioritizer
For founders who don't know where to start with paid ads. Analyzes ICP, competitor ad presence, budget constraints, and product type to recommend which 1-2 paid channels to start with and provides a 90-day ramp plan. Prevents the common mistake of spreading a small budget across too many platforms.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
email-finder-hunter
Email finder and verifier - find emails, verify deliverability, discover companies.
lead-discovery
Orchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies competitors, builds ICP, and routes to signal skills with pre-filled inputs.
render-mosaic-grid-reveal
Render a 'mosaic-grid-reveal' video from a config — a real-DOM FULL-BLEED N×N mosaic of real product tiles that pops in one tile at a time (scatter order, ease-out-back overshoot), the grid clears, then the brand wordmark builds line-by-line followed by a sub-label, tagline, and CTA; frame-stepped via Playwright and…