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/ai-debugger-inc/aidb/skill-developernpx skills add ai-debugger-inc/aidb --skill skill-developergit clone --depth 1 https://github.com/ai-debugger-inc/aidbWhat 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 | $0.00091 | $0.02934 |
| Opus 5 | $0.00046 | $0.01467 |
| Sonnet 5 | $0.00018 | $0.00587 |
| Haiku 4.5 | $0.00009 | $0.00293 |
Grade A, and why
skill-developer 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 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.
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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Developer Guide
Purpose
Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and progressive disclosure pattern.
When to Use This Skill
Automatically activates when you mention:
- Creating or adding skills
- Modifying skill triggers or rules
- Understanding how skill activation works
- Debugging skill activation issues
- Working with skill-rules.json
- Hook system mechanics
- Claude Code best practices
- Progressive disclosure
- YAML frontmatter
- 500-line rule
Related Skills
When building skills, reference:
- testing-strategy - Skills should be tested with real scenarios before extensive documentation
- code-reuse-enforcement - Skills should reference existing patterns/utilities from the codebase
Relationship to CLAUDE.md
Division of Responsibilities:
- CLAUDE.md: Global project context, high-level architecture, universal style rules
- Skills: Domain-specific detailed guidance, patterns, procedures (triggered by context)
- skill-developer: Meta-skill that maintains the skills system and explains its relationship to CLAUDE.md
When to Update:
- Global style rules (numpy docstrings, no emojis, use venv) → Update CLAUDE.md
- Domain patterns/practices (test patterns, adapter design) → Update relevant skill
- Skill system mechanics (triggers, hooks, 500-line rule) → Update skill-developer
Integration:
- CLAUDE.md references skills for detailed guidance (1-line pointers)
- Skills don't reference CLAUDE.md (avoid circular dependencies)
- skill-developer explains the complete hierarchy (this section)
Progressive Disclosure Hierarchy:
CLAUDE.md (Global Context)
↓ references
Skills (Domain Guidance)
↓ maintained by
skill-developer (Meta-Skill)
System Overview
The skills system uses a two-tier architecture (meta-skills vs domain skills) with automatic injection to seamlessly provide domain-specific context.
What ships with it
5 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.
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 · 404 lines · 91 tokens per session scan A 5306d41162c8
skill-developer is a skill published in the GitHub repository ai-debugger-inc/aidb (21 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,934 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
hugging-face-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.