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/dev-cli-developmentnpx skills add ai-debugger-inc/aidb --skill dev-cli-developmentgit 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 | $0.00071 | $0.03664 |
| Opus 5 | $0.00036 | $0.01832 |
| Sonnet 5 | $0.00014 | $0.00733 |
| Haiku 4.5 | $0.00007 | $0.00366 |
Grade A, and why
dev-cli-development 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Wrong**: `subprocess.run(["cmd"])` How it starts
The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev-CLI Development Guide
Purpose
The AIDB dev-cli (src/aidb_cli/) is a Click-based command-line interface for AIDB development workflows. This skill guides developers in:
- Adding new CLI commands and command groups
- Creating reusable services following BaseService pattern
- Using custom decorators (@handle_exceptions, @require_repo_context)
- Integrating with Docker, test, and adapter systems
- Following Click framework best practices
- Proper error handling and output formatting
When to Use This Skill
Auto-activates when:
- Editing files in
src/aidb_cli/ - Mentioning "dev-cli", "CLI command", "Click", "CliOutput"
- Adding commands, services, or CLI utilities
- Working with test orchestration or Docker integration
Related Skills
When developing CLI commands, you may also need:
- testing-strategy - CLI orchestrates test execution via test coordinator service
- code-reuse-enforcement - CLI must use existing constants and avoid magic strings
Architecture Overview
For comprehensive architecture details, see docs/developer-guide/cli-reference.md and source code in src/aidb_cli/.
Component Structure
src/aidb_cli/
├── commands/ # CLI command definitions (13 modules)
├── services/ # Business logic services (41+ files)
├── managers/ # High-level orchestration (singleton pattern)
├── core/ # Decorators, utilities, constants, param types
└── generators/ # Code generation for test scenarios
Key Patterns
- Commands - Thin wrappers that delegate to services
- Services - Reusable business logic with CommandExecutor
- Managers - Singleton orchestrators for complex workflows
- Context Injection - Dependencies via Click's
ctx.obj - Unified Error Handling -
@handle_exceptionsdecorator - Dynamic Parameter Types - Custom types with shell completion
Quick Start: Adding a Command
Step 1: Create Command File
Create src/aidb_cli/commands/mycommand.py:
What ships with it
6 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 · 513 lines · 71 tokens per session scan A 16e6a845a23e
dev-cli-development is a skill published in the GitHub repository ai-debugger-inc/aidb (21 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 3,664 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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…
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.
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.
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.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.