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.
git clone --depth 1 https://github.com/TechNickAI/ai-coding-configWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/technickai/ai-coding-config/repo-tooling)<a href="https://agentmods.dev/commands/technickai/ai-coding-config/repo-tooling"><img src="https://agentmods.dev/badge/commands/technickai/ai-coding-config/repo-tooling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/technickai/ai-coding-config/repo-tooling"><img src="https://agentmods.dev/badge/commands/technickai/ai-coding-config/repo-tooling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00030 | $0.03549 |
| Opus 5.5 | $0.00012 | $0.01420 |
| Sonnet 5.5 | $0.00006 | $0.00710 |
| Haiku 4.5 | $0.00003 | $0.00355 |
Grade A, and why
repo-tooling 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 8d 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Tooling Setup
Configures projects with professional development tooling based on detected language:
- TypeScript/Next.js: ESLint, Prettier, Husky, GitHub Actions
- Python: Ruff, MyPy, pre-commit, GitHub Actions (templates coming soon)
For language detection:
- JavaScript/TypeScript: package.json exists
- TypeScript specifically: tsconfig.json or .ts files present
- Next.js framework: next.config.js or next.config.mjs exists
- Python: pyproject.toml, setup.py, or requirements.txt exists
- Python framework: settings.py (Django), main.py with FastAPI imports, etc.
For existing tooling:
- Linting: eslint.config.mjs, .eslintrc.*, pyproject.toml with [tool.ruff]
- Formatting: .prettierrc, prettier.config.*, pyproject.toml with [tool.black]
- Type checking: tsconfig.json with strict, mypy.ini, pyproject.toml with [tool.mypy]
- Git hooks: .husky/ directory, .pre-commit-config.yaml
- CI/CD: .github/workflows/ directory
- Package manager: Lock files (pnpm-lock.yaml, package-lock.json, yarn.lock, poetry.lock, requirements.txt)
Store findings for recommendation phase.
For TypeScript/JavaScript projects:
- Check package.json engines.node field first (respect existing constraints)
- If not specified, fetch latest LTS Node version:
- Use WebFetch on https://nodejs.org/dist/index.json
- Find latest entry where lts property is not false
- Extract major version number (e.g., 22 from v22.12.0)
- Fall back to current installed version: node --version
- Store as NODE_VERSION for GitHub Actions workflow
For Python projects (future):
- Check pyproject.toml python requirement or .python-version file
- If not specified, fetch latest stable Python version from python.org
- Fall back to current installed: python --version
- Store as PYTHON_VERSION for GitHub Actions
Detect package manager from lock files and configuration:
- pnpm: pnpm-lock.yaml exists, extract version from packageManager field if available
- npm: package-lock.json exists
- yarn: yarn.lock exists
- poetry: poetry.lock exists
- pip: requirements.txt exists
Package versions (eslint, prettier, ruff, etc.) use caret ranges in templates - let package manager resolve to latest compatible.
For TypeScript/Next.js projects:
"I can set up professional development tooling for this {framework} project:
{List what will be added based on what's missing:} ✓ ESLint 9 + Prettier 3 for code quality ✓ TypeScript strict mode for enhanced type safety ✓ Pre-commit hooks (Husky + lint-staged) - auto-fix on commit ✓ Pre-push validation (type-check, format, test) ✓ GitHub Actions CI/CD (build, test, quality checks) ✓ Claude Code review on pull requests
Configuration:
- Node.js {detected-version} ({source: from package.json engines / latest LTS / installed})
- {detected-package-manager} {version}
- Latest stable packages: eslint@^9, prettier@^3, husky@^9
{If any tooling already exists:} Already configured: {list existing tools} Will preserve your existing configurations and add missing pieces."
For Python projects:
"Python project detected. Templates for Python tooling setup are coming soon. For now, I recommend manually setting up: ruff for linting, black for formatting, mypy for type checking, and pre-commit for git hooks."
Use AskUserQuestion with single decision point:
- Header: "Setup"
- Question: "Proceed with this setup?"
- Options:
- "Yes, set it up" - Description: "Use these recommendations and proceed immediately"
- "Let me customize" - Description: "Choose which features to enable and git strategy"
- multiSelect: false
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.
- 8d ago First seen · 442 lines · 30 tokens per session scan A 83cab760ab88
repo-tooling is a command published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 8d ago), licensed MIT. It adds 30 tokens to every session and 3,549 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-22.
Other commands, from other repositories
spawn-team
Spawn the default agent team for this project. Creates a coordinated team of agents that implement features in parallel following the strict TDD pipeline.
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
ship
Mechanical pre-deploy gate — tests, build, tree state.
feature-implement-execute
Phase 4 of develop: Execute the implementation plan with per-task TDD, quality gates, and completion verification.
audit-mirage-analyze
Phases 2-3 and 7 of auditing-green-mirage: systematic line-by-line audit, the Green Mirage Patterns, named assertion shapes, and the fix-verification Test Adversary prompt.
fix-tests-execute
Phase 2 of fixing-tests: Fix Execution - investigate, classify, fix, verify, and commit each work item.