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/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/skills/hamzapixl/pixl-ai/makefile"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/makefile.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 | $0.00048 | $0.01316 |
| Opus 5.5 | $0.00019 | $0.00526 |
| Sonnet 5.5 | $0.00010 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
makefile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Creates a Makefile following pixl-crew conventions. The focus is on non-obvious patterns — self-documenting help targets, monorepo-aware workspace targets, and correct integration with uv/bun/Docker Compose.
Step 1: Discovery
- Detect project language, build system, and package manager
- Identify existing scripts in
package.json,pyproject.toml, etc. - Check for Docker/Docker Compose, CI/CD, and deployment tools
- Determine if this is a monorepo (multiple
package.json/pyproject.tomlfiles, workspace config) - Check for
.envfiles that need loading
Step 2: Generate Makefile
Structure
Follow this ordering convention:
# 1. .PHONY declaration — ALL non-file targets, one line
.PHONY: setup install dev build test lint format typecheck clean deploy docker-build docker-up help
# 2. Environment loading
ifneq (,$(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.
- 1mo 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 6mo ago), licensed MIT. It adds 48 tokens to every session and 1,316 once invoked, about $0.0002 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 2026-09-03.
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…
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.
hatch3r-cli-toolbox
Category-indexed reference for 34 specialist CLI tools beyond the always-on five (ripgrep, jq, gh, fd, fzf). Use to pick the right tool for HTTP clients, ai-chat, structural-search, sed-style edits, data ops, browser automation, container ops, and more.
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.
cleanup-discipline
Disciplined disk-cleanup workflow for reclaiming storage without destroying live runtimes, unpushed work, or unrecoverable data. Use for ANY disk-space cleanup, storage reclamation, "what can we delete", purge/prune campaigns, or when asked to free up space — survey, classify, verify, capture, delete, report.
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…