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 qhkm/zeptoclaw --skill skill-creatorgit clone --depth 1 https://github.com/qhkm/zeptoclawWrote 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/qhkm/zeptoclaw/skill-creator)<a href="https://agentmods.dev/skills/qhkm/zeptoclaw/skill-creator"><img src="https://agentmods.dev/badge/skills/qhkm/zeptoclaw/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/qhkm/zeptoclaw/skill-creator"><img src="https://agentmods.dev/badge/skills/qhkm/zeptoclaw/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Rogue Agent · line 48 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Output Handling · line 98 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00027 | $0.01333 |
| Opus 5 | $0.00014 | $0.00666 |
| Sonnet 5 | $0.00005 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00133 |
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 11d 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.
metadata: {"zeptoclaw":{"emoji":"📦","requires":{"bins":["curl"],"any_bins":[],"env":[]},"install":[],"always":false,"os":[]}} How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Guide users through designing and building ZeptoClaw skills. Follow these six steps in order — do not skip ahead.
Step 1 — Gather Concrete Examples
Before designing anything, ask the user for 3-5 real queries or tasks the skill should handle. Collect actual example inputs and expected behaviors. Do not proceed until you have concrete use cases — vague ideas produce vague skills.
Step 2 — Analyze Reusable Content
For each example, ask: "What would need to be looked up, computed, or re-done each time without this skill?" The answers become the skill's content. Discard anything the agent already knows how to do without help.
Categories of reusable content:
- Commands/scripts — exact CLI invocations, API calls, shell pipelines
- References — URLs, lookup tables, domain-specific facts the agent wouldn't know
- Templates — message formats, boilerplate, structured output patterns
- Workflows — multi-step procedures with specific ordering constraints
If nothing survives this filter, the user may not need a skill — say so.
Step 3 — Choose Structure and Freedom Level
Pick the structural pattern that best fits the content:
| Pattern | When to use | Example |
|---|---|---|
| Workflow | Ordered multi-step process | deploy-docker, release-notes |
| Task-based | Independent tasks, any order | shopee, github |
| Reference | Lookup information | weather, api-cheatsheet |
| Capabilities | Agent behaviors/personas | code-reviewer, translator |
Then assign a freedom level to each piece of content:
- High freedom (text instructions): Multiple valid approaches exist. Let the agent decide how to execute. Use for guidelines, principles, and flexible tasks.
- Medium freedom (pseudocode or parameterized commands): A preferred pattern exists but details vary. Use for common workflows with variable inputs.
- Low freedom (exact commands/scripts): Fragile or error-prone operations where precision matters. Use for API calls with specific syntax, deployment commands, or data formats.
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.
- 11d ago First seen · 124 lines · 27 tokens per session scan A 339aec6a6858
skill-creator is a skill published in the GitHub repository qhkm/zeptoclaw (651 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,333 once invoked, about $0.0001 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 skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
llama-cpp
Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quantization (2–8 bit with K-quants and imatrix). Covers CLI, Python bindings, OpenAI-compatible server, and Ollama/LM Studio integration. Use for edge deployment, M1/M2/M3/M4 Macs, CUDA-less…
linear
Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
github-auth
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.