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 sawrus/agent-guides --skill general-dev-toolsgit clone --depth 1 https://github.com/sawrus/agent-guidesWrote 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/sawrus/agent-guides/general-dev-tools)<a href="https://agentmods.dev/skills/sawrus/agent-guides/general-dev-tools"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/general-dev-tools.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 | $0.00031 | $0.02066 |
| Opus 5 | $0.00015 | $0.01033 |
| Sonnet 5 | $0.00006 | $0.00413 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade C, and why
general-dev-tools scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null; true How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Dev Tools Skill
Expertise: Git, Docker Compose, Makefile, GitHub Actions, GitLab CI, shell scripting, linting, formatting, pre-commit hooks.
Mindset
- Repeatability: All setup is automatable via
maketargets.make install && make devmust work on a clean machine. - Portability: Commands work consistently across developer machines and CI.
- Security: Never commit secrets. Use env vars; secret managers for production.
- Fail loudly: Check exit codes; prefer explicit error messages over silent failures.
Git Patterns
Branch naming
feature/<task-id>-short-desc # e.g. feature/PROJ-42-add-search
fix/<task-id>-short-desc # e.g. fix/PROJ-55-null-pointer
chore/<description> # e.g. chore/upgrade-dependencies
release/<version> # e.g. release/2.4.0
Commit convention (Conventional Commits)
feat(scope): add user search endpoint # new feature
fix(auth): handle expired token on refresh # bug fix
chore(deps): upgrade pydantic to 2.x # maintenance
docs(api): update endpoint reference # docs only
test(orders): add edge case for zero qty # tests only
refactor(repo): extract pagination helper # no behavior change
Common operations
# Create and track feature branch
git checkout -b feature/PROJ-42-add-search
git push -u origin feature/PROJ-42-add-search
# Rebase on latest main before PR
git fetch origin
git rebase origin/main
# Squash last N commits before merge
git rebase -i HEAD~3
# Undo last commit (keep changes staged)
git reset --soft HEAD~1
# Find which commit introduced a bug
git bisect start
git bisect bad HEAD
git bisect good <known-good-sha>
.gitignore essentials
# Python
__pycache__/ *.pyc .venv/ .env *.egg-info/ dist/ .pytest_cache/ .mypy_cache/
# Node
node_modules/ dist/ .env .env.local coverage/
# General
.DS_Store *.log .idea/ .vscode/ *.swp
Makefile Patterns
Standard target set (required for all projects)
.PHONY: install dev test lint fmt clean help
install: ## Install all dependencies
pip install -r requirements.txt -r requirements-dev.txt
pre-commit install
dev: ## Start local development environment
docker compose up -d
uvicorn src.main:app --reload --port 8000
test: ## Run test suite
pytest tests/ -v --cov=src --cov-report=term-missing
lint: ## Run linter (zero-tolerance)
ruff check src/ tests/
mypy src/
fmt: ## Format code in-place
ruff format src/ tests/
ruff check --fix src/ tests/
clean: ## Remove generated files
find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null; true
rm -rf .coverage htmlcov/ dist/ build/
help: ## Show this help
@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf " \033[36m%-15s\033[0m %s\n", $$1, $$2}'
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 · 325 lines · 31 tokens per session scan C b81384494af4
general-dev-tools is a skill published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 2,066 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
ax-extract-workflow
Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built.
pr-review
Reviews a GitHub pull request and posts inline comments plus one consolidated summary, adapting to any codebase by discovering the project's own test runner, requirement specs, and architecture conventions before running six specialized review agents in parallel. Stack-agnostic across language and framework; targets…
commit
Quality gate runs FIRST. Do NOT commit if any gate fails.
gate
MANDATORY before every commit and push. All gates must pass — Gates 1–3 always run; Gates 4 (Docker) and 5 (Cloud) run only when applicable. Do NOT proceed if any gate fails — fix the issue first.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.