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 commands/technickai/claude_telemetry/ai-coding-configgit clone --depth 1 https://github.com/TechNickAI/claude_telemetryWhat 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 | $0.00013 | $0.01822 |
| Opus 5 | $0.00006 | $0.00911 |
| Sonnet 5 | $0.00003 | $0.00364 |
| Haiku 4.5 | $0.00001 | $0.00182 |
Grade A, and why
ai-coding-config 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 3d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Configuration
Manages reusable AI configurations across machines and projects.
Understanding the System
First, get context about what ai-coding-config does:
- If ~/.ai_coding_config exists: Read ~/.ai_coding_config/README.md
- If not: Fetch and read https://raw.githubusercontent.com/TechNickAI/ai-coding-config/main/README.md
The system contains Cursor rules, Claude commands, Claude Code Agents, personalities, and GitHub workflows in ~/.ai_coding_config. This command copies (not reads/rewrites) relevant configurations into projects and keeps them synced.
Arguments (Optional)
If user provides 'update' argument (/ai-coding-config update), skip to Goal 6.
Otherwise, proceed conversationally through the setup goals.
Primary Goals
Goal 1: Ensure ~/.ai_coding_config Exists and Is Up to Date
If the repo isn't cloned yet, clone it:
git clone https://github.com/TechNickAI/ai-coding-config.git ~/.ai_coding_config
If it already exists, update it:
cd ~/.ai_coding_config && git pull
Then offer to set up the current project.
Goal 2: Understand the Project Context
Figure out what kind of project this is and what it needs:
- Detect language/framework (Python/Django/FastAPI, TypeScript/React/Next.js, etc.)
- Look for existing configurations to avoid duplicates
- Understand the project's specific needs (API? Web app? CLI tool?)
Be specific about frameworks, not just languages. Django projects need different rules than FastAPI projects.
Goal 3: Present Relevant Options
Show the user what's available that matches their project:
- Group rules by relevance (framework-specific first, then universal)
- For each rule, read the
descriptionfield from its frontmatter to explain what it does - Present personality options (one personality, or none) with descriptions from frontmatter
- Present Claude Code Agents (default to all, but let them choose) with descriptions from frontmatter
- Mention that VSCode settings, Prettier config, and GitHub workflows will be included by default
- Separate personalities and agents from rules in your presentation
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.
- 3d ago First seen · 196 lines · 13 tokens per session scan A 99565d668439
ai-coding-config is a command published in the GitHub repository TechNickAI/claude_telemetry (30 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 1,822 once invoked, about $0.0001 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 commands, from other repositories
worktree-check
Check current worktree status, branch, and assigned task.
five
Apply the Five Whys root cause analysis technique to investigate an issue.
status
Show current Craft progress — cycles, stories, backlog in a rich dashboard view.
story-implement-auto
Autonomous story implementation — auto-picks stories, chains through cycle, no interactive prompts.
pr-review
Use when responding to PR review comments for specified pull request(s).
ask
Consult a craft agent. Routes your question to the best mind in the workshop - not a menu, a recommendation.