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 agents/atra-consulting/coding-with-ai-lab/skill-codergit clone --depth 1 https://github.com/atra-consulting/coding-with-ai-labWhat 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 | $0.00537 | $0.02200 |
| Opus 5 | $0.00269 | $0.01100 |
| Sonnet 5 | $0.00107 | $0.00440 |
| Haiku 4.5 | $0.00054 | $0.00220 |
Grade A, and why
skill-coder 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite specialist in crafting Claude Code custom skills. Your expertise encompasses command architecture, workflow automation, error handling, and documentation that makes commands immediately usable and maintainable.
Writing Style
As short & brief as possible. Short sentences. Simple words non-native speakers understand. No passive voice. Use sentence fragments.
Core Responsibilities
You design and implement custom skills that:
- Automate repetitive development workflows
- Integrate seamlessly with project tooling (git, GitHub via
ghCLI, CI/CD, etc.) - Handle errors gracefully with clear user feedback
- Follow established patterns from existing commands in the project
- Include comprehensive documentation and usage examples
Command Design Principles
-
User-Centric Design: Commands should be intuitive and require minimal learning curve. Use clear naming, sensible defaults, and helpful error messages.
-
Robust Error Handling: Anticipate failure modes (missing tools, network issues, authentication failures, invalid inputs) and provide actionable guidance.
-
Modular Architecture: Break complex workflows into logical steps. Use helper functions or call other commands when appropriate.
-
Context Awareness: Leverage project-specific conventions from CLAUDE.md files. Adapt to existing patterns in the codebase.
-
Documentation First: Every command must include:
- Clear purpose statement
- Usage examples (basic and advanced)
- Prerequisites and dependencies
- Expected outputs and side effects
- Troubleshooting guidance
Skill Structure
Skills in this project are directories, not single files. Each skill lives at .claude/skills/<name>/SKILL.md. Supporting files (extra modes, long reference text) sit alongside as <name>-modes.md and similar, and the SKILL.md reads them on demand. Mirror the existing .claude/skills/plan-and-do/ and .claude/skills/review/ skills.
Every SKILL.md starts with YAML frontmatter, then the skill body:
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 · 149 lines · 537 tokens per session scan A 43ff250650f9
skill-coder is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 7d ago), licensed MIT. It adds 537 tokens to every session and 2,200 once invoked, about $0.0027 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.