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/heoooooon/lazy-starter-kit/agents-mdgit clone --depth 1 https://github.com/Heoooooon/lazy-starter-kitWhat 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 | $0.00130 | $0.00130 |
| Opus 5 | $0.00065 | $0.00065 |
| Sonnet 5 | $0.00026 | $0.00026 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade C, and why
lazy-starter-kit AGENTS.md 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 3d 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.
- Never run `rm -r`, `rm -rf`, `rm -R`, or `rm --recursive` directly. What it actually says
Safety rules for coding agents
- Never run
rm -r,rm -rf,rm -R, orrm --recursivedirectly. - Use
lazy-safe-rmfor recursive cleanup. It only accepts strict descendants of the current Git workspace. - Never bypass the Codex or Claude Code shell-safety hook, including through
/bin/rm,sudo,env,xargs, or a nested shell. - Product cleanup code must use
safe_rm_rf_underon macOS/Linux orRemove-KitTreeon Windows. - Preserve unrelated working-tree changes and local-only agent settings.
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.
- 3d ago First seen · 8 lines · 130 tokens per session scan C f97fd46f2d0a
lazy-starter-kit AGENTS.md is an instructions file published in the GitHub repository Heoooooon/lazy-starter-kit (81 stars, last pushed 3d ago), licensed MIT. It adds 130 tokens to every session, about $0.0006 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 2026-08-30.
Other instructions, from other repositories
base AGENTS.md
Instructions for basefoundry/base, covering ai agent guidance, working agreement, github workflow, repository release contract and validation.
base copilot-instructions.md
Instructions for basefoundry/base: Use AGENTS.md as the canonical workflow guidance for Base. These instructions exist to point Copilot at the same repository-owned rules used by other coding agents; they do not replace AGENTS.md, CONTRIBUTING.md, STANDARDS.md, or the .ai-context/ orientation files.
openscreen AGENTS.md
Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
OpenNOW copilot-instructions.md
Copilot instructions for OpenCloudGaming/OpenNOW, covering copilot instructions for opennow, project scope, build, check, and packaging commands, from repository root and from opennow-stable/.
tabularis AGENTS.md
AGENTS.md instructions for TabularisDB/tabularis, covering agents.md, directives, gitnexus — code intelligence, always do and never do.
maroto AGENTS.md
Instructions for johnfercher/maroto, covering agent instructions, skills, definition of done, contributing commands and tool dependencies.