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 skills/bug-ops/zeph/skill-creatornpx skills add bug-ops/zeph --skill skill-creatorgit clone --depth 1 https://github.com/bug-ops/zephWhat 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 | $0.00075 | $0.00911 |
| Opus 5 | $0.00037 | $0.00456 |
| Sonnet 5 | $0.00015 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade B, and why
skill-creator scanned grade B 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
4. **Security first** — never include secrets, credentials, or destructive commands without warnings How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Create a new skill following the agentskills.io specification (https://agentskills.io/specification).
Step 1: Gather requirements
Ask the user:
- What should the skill do?
- What tools or commands does it need?
- Does it need references, scripts, or assets?
If the user already provided enough context, skip asking and proceed.
Step 2: Choose a name
Rules for the name field:
- 1-64 characters
- Lowercase letters, numbers, hyphens only (
a-z,0-9,-) - Must NOT start or end with
- - Must NOT contain consecutive hyphens (
--) - Must match the parent directory name
Step 3: Write the description
Rules for the description field:
- 1-1024 characters
- Must describe WHAT the skill does AND WHEN to use it
- Include keywords that help semantic matching
Good:
description: Extract text and tables from PDF files, fill PDF forms, and merge multiple PDFs. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction.
Bad:
description: Helps with PDFs.
Step 4: Create the directory structure
.zeph/skills/<skill-name>/
├── SKILL.md # Required
├── scripts/ # Optional: executable scripts
├── references/ # Optional: detailed docs loaded on demand
└── assets/ # Optional: templates, schemas, data files
Step 5: Write SKILL.md
Use this template:
---
name: <skill-name>
description: <what it does and when to use it>
compatibility: <only if environment requirements exist>
metadata:
author: zeph
version: "1.0"
---
# <Skill Title>
<One-line summary of what this skill does.>
## Step 1: <First action>
<Instructions with code blocks showing exact commands or tool invocations.>
## Step 2: <Next action>
<Continue step-by-step. Keep instructions concrete and unambiguous.>
Optional frontmatter fields
| Field | When to use |
|---|---|
license |
Skill has specific licensing terms |
compatibility |
Skill requires specific binaries, network, or environment |
metadata |
Extra key-value pairs (author, version, tags) |
allowed-tools |
Pre-approve specific tools (experimental) |
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 · 127 lines · 75 tokens per session scan B 8724edac67c7
skill-creator is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 911 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify
Run Chimeraforge's canonical verification gate end-to-end and report the real output before claiming work done or committing. Failing output gets pasted, fixed, and re-run — never summarized away.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
greptimedb-release
Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).