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 skills add hamzaPixl/pixl-ai --skill makefilegit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/skills/hamzapixl/pixl-ai/makefile)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/makefile"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/makefile.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01316 |
| Opus 5 | $0.00024 | $0.00658 |
| Sonnet 5 | $0.00010 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
makefile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Creates a Makefile following pixl-crew conventions. The focus is on non-obvious patterns — self-documenting help targets, monorepo-aware workspace targets, and correct integration with uv/bun/Docker Compose.
Step 1: Discovery
- Detect project language, build system, and package manager
- Identify existing scripts in
package.json,pyproject.toml, etc. - Check for Docker/Docker Compose, CI/CD, and deployment tools
- Determine if this is a monorepo (multiple
package.json/pyproject.tomlfiles, workspace config) - Check for
.envfiles that need loading
Step 2: Generate Makefile
Structure
Follow this ordering convention:
# 1. .PHONY declaration — ALL non-file targets, one line
.PHONY: setup install dev build test lint format typecheck clean deploy docker-build docker-up help
# 2. Environment loading
ifneq (,$(wildcard .env))
include .env
export
endif
# 3. Variables with ?= defaults (overridable from CLI)
PORT ?= 3000
ENV ?= development
BUMP ?= patch
# 4. Composite targets first (setup, ci)
# 5. Dev targets (dev, build, clean)
# 6. Quality targets (test, lint, format, typecheck)
# 7. Deploy targets (deploy, docker-*)
# 8. help target LAST
Self-Documenting Help Target
Every target MUST have a ## Comment suffix. The help target auto-generates docs from these:
setup: install ## Full setup: install deps + configure
@echo "Ready."
help: ## Show available targets
@grep -E '^[a-zA-Z_-]+:.*?## ' Makefile | awk 'BEGIN {FS=":.*?## "};{printf " %-18s %s\n",$$1,$$2}'
Package Manager Targets
uv (Python):
PYTEST := uv run python -m pytest --import-mode=importlib
install: ## Install workspace packages
uv sync --all-extras
test: ## Run all tests
$(PYTEST)
lint: ## Lint check
uv run ruff check .
format: ## Auto-format
uv run ruff check --fix .
uv run ruff format .
bun (TypeScript):
install: ## Install dependencies
bun install
dev: ## Start dev server
bun run dev
build: ## Production build
bun run build
test: ## Run tests
bun test
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.
- 4d ago First seen · 165 lines · 48 tokens per session scan A 2d67e8e7ffb5
makefile is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,316 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
whendone-plus
Automatically notify the user when long-running terminal commands finish (npm test, docker build, git push, etc.). The agent monitors command execution and sends a desktop notification on completion if the command ran longer than threshold (default 10s). Use when user asks to "notify me when done", "desktop…
gobbler-setup
Installs, configures, and troubleshoots Gobbler. Triggers on install gobbler, setup, not working, connection refused, Docker/service failures, ffmpeg problems, browser relay failures, or diagnostic requests.
system-environment-setup
Build reproducible developer environments for real projects: local toolchains, runtime versions, Docker Compose or dev containers, onboarding flows, local service parity, bootstrap scripts, and environment troubleshooting. Use when the user needs a repo to run consistently across machines, containers, or staged…
vscode-workspace-setup
Configures VS Code workspaces with optimal settings, extensions, tasks, and debugging for team consistency. Use when users request "VS Code setup", "workspace settings", "team VS Code config", "editor configuration", or "devcontainer setup".
developer-experience-patterns
Use when designing or reviewing developer tooling, monorepo structure, dev environments, onboarding flows, or internal platforms — covers Monorepo tooling (Nx/Turborepo), dev containers, golden path / platform engineering, local-prod parity, fast feedback loops, DX-first API design, developer onboarding, and DX…
terminal-execution
Guide for using the execute tool to run shell commands in workspace. Use when agent needs to: build/test code, run scripts, check system status, install dependencies, or execute deployment commands.