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 instructions/mikkovihonen/quadletman/claude-mdgit clone --depth 1 https://github.com/mikkovihonen/quadletmanWrote 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/instructions/mikkovihonen/quadletman/claude-md)<a href="https://agentmods.dev/instructions/mikkovihonen/quadletman/claude-md"><img src="https://agentmods.dev/badge/instructions/mikkovihonen/quadletman/claude-md.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 | $0.16291 | $0.16291 |
| Opus 5 | $0.08145 | $0.08145 |
| Sonnet 5 | $0.03258 | $0.03258 |
| Haiku 4.5 | $0.01629 | $0.01629 |
Grade B, and why
quadletman CLAUDE.md scanned grade B with 2 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo/wheel users. Admin operations use the authenticated user's sudo credentials for Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `subprocess.run(mutating_cmd, ...)` | `host.run(mutating_cmd, ...)` | How it starts
The opening of the file, as written. The whole thing — 994 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — quadletman
What This Is
quadletman is a FastAPI web UI (HTMX + Tailwind) for managing Podman Quadlet container
services on a Linux host. It runs as a dedicated quadletman system user via a systemd
service and uses PAM-based HTTP Basic Auth restricted to
sudo/wheel users. Admin operations use the authenticated user's sudo credentials for
privilege escalation. See README.md for full user-facing documentation.
Dev Commands
uv sync --group dev # install all deps including dev tools
./scripts/run_dev.sh # run as qm-dev user with dev-isolated data
uv run ruff check quadletman/ # lint
uv run ruff format quadletman/ # format
uv run pytest # run test suite (must NOT run as root)
uv run pre-commit run --all-files # run all checks (fail_fast: lint → format → tests)
TAILWINDCSS_VERSION=v4.2.2 uv run tailwindcss -i quadletman/static/src/app.css \
-o quadletman/static/src/tailwind.css --minify
# rebuild Tailwind CSS — re-run after adding new utility
# classes to any template; commit the output file
# TAILWINDCSS_VERSION must match ci.yml and .pre-commit-config.yaml
uv run pybabel extract -F babel.cfg -o quadletman/locale/quadletman.pot .
# re-extract translatable strings after adding/changing strings
uv run pybabel update -i quadletman/locale/quadletman.pot -d quadletman/locale -D quadletman
# update existing .po files with new/changed strings
uv run pybabel compile -d quadletman/locale -D quadletman
# compile .po → .mo for runtime use (run after updating)
# See docs/localization.md for the full localization workflow
npm test # run JavaScript unit tests (Vitest, Node 20+ required)
Pre-commit hooks run automatically on git commit and auto-fix what they can. The pipeline
uses fail_fast: true so a ruff lint failure stops the pipeline before pytest runs. Pytest
only triggers when files under quadletman/ or tests/ are staged — docs-only or
config-only commits skip the test suite. Never use --no-verify to skip hooks.
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.
- 5d ago First seen · 994 lines · 16,291 tokens per session scan B 7090aa0d6213
quadletman CLAUDE.md is an instructions file published in the GitHub repository mikkovihonen/quadletman (56 stars, last pushed yesterday), licensed MIT. It adds 16,291 tokens to every session, about $0.0815 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
nuclear AGENTS.md
AGENTS.md instructions for nukeop/nuclear, covering agents.md, project overview, packages, commands and development.
Pake copilot-instructions.md
Copilot instructions for tw93/Pake, a project described as: 🤱🏻 Turn any webpage into a desktop app with one command.
swift-tui AGENTS.md
AGENTS.md instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.
agent-zero AGENTS.md
AGENTS.md instructions for agent0ai/agent-zero, covering agent zero dox, purpose, project, root ownership and project-wide contracts.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.
AutoControlGUI CLAUDE.md
Claude Code instructions for Integration-Automation/AutoControlGUI, covering claude.md — autocontrol, project overview, architecture, development commands and feature delivery rules.