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/krystianmarek/ai-assisted-development/agents-mdgit clone --depth 1 https://github.com/KrystianMarek/ai-assisted-developmentWrote 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/krystianmarek/ai-assisted-development/agents-md)<a href="https://agentmods.dev/instructions/krystianmarek/ai-assisted-development/agents-md"><img src="https://agentmods.dev/badge/instructions/krystianmarek/ai-assisted-development/agents-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 | $0.06161 | $0.06161 |
| Opus 5 | $0.03080 | $0.03080 |
| Sonnet 5 | $0.01232 | $0.01232 |
| Haiku 4.5 | $0.00616 | $0.00616 |
Grade F, and why
ai-assisted-development AGENTS.md scanned grade F with 4 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 bash -c 'curl -L https://github.com/dolthub/dolt/releases/latest/download/install.sh | sudo bash' Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
sudo bash -c 'curl -L https://github.com/dolthub/dolt/releases/latest/download/install.sh | sudo bash' Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf directory # NOT: rm -r directory Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sudo bash -c 'curl -L https://github.com/dolthub/dolt/releases/latest/download/install.sh | sudo bash' How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to any agent working in this repository — Claude Code, Codex, OpenCode, Cursor, Aider, and others.
AGENTS.mdis the canonical source.CLAUDE.mdis a symbolic link to this file so Claude Code reads the same instructions. Edits to either path land in the same content — prefer editingAGENTS.mddirectly.
⏱️ Project Initialization Checklist — REMOVE THIS SECTION AFTER COMPLETION
Shortcut: from a checkout of this template, run
./adopt.sh --target /path/to/your/repoto automate steps 1–5 below. Steps 6 (Project Overview, Dev Conventions, delete this checklist) are still manual. The manual walkthrough remains authoritative if anything inadopt.shfails.
This section is temporal: it runs once, when the project is first cloned or scaffolded from this template. Work through it with the user, tick each box, and delete this whole section from AGENTS.md when finished so it does not nag every subsequent session.
1. Install git pre-commit hooks
The rule "Work is NOT complete until git push succeeds" (see Session Completion below) relies on local hooks that catch lint/format/test failures before a commit is created. Without hooks, broken code reaches the remote and the rule becomes aspirational.
Action:
- Confirm
pre-commitis available:pre-commit --version || pip install pre-commit # or: uv tool install pre-commit - Create
.pre-commit-config.yamlwith at minimum:trailing-whitespace,end-of-file-fixer,check-merge-conflict,check-yaml- a language-appropriate linter (
rufffor Python,golangci-lintfor Go,eslint/biomefor JS/TS, etc.) - Pin revisions to the latest at adoption time. The template ships reasonable defaults but they may be months behind — check each repo for the current tag.
- Register the hook:
pre-commit install - Verify it fires:
pre-commit run --all-files
If the user prefers another runner (prek, husky, lefthook), swap it in — but keep the guarantee: no commit lands without passing lint/format checks.
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 · 449 lines · 6,161 tokens per session scan F 0f465a698c94
ai-assisted-development AGENTS.md is an instructions file published in the GitHub repository KrystianMarek/ai-assisted-development (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 6,161 tokens to every session, about $0.0308 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
daisyui code_generation_with_git.instructions.md
Instructions for saadeghi/daisyui, covering activation, initial setup, development loop, error handling and session end.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
dario CLAUDE.md
Claude Code instructions for askalf/dario, covering dario — notes for claude code (and other llm coding agents), commits and prs, style, scope and when in doubt, ask.
granite.build AGENTS.md
AGENTS.md instructions for ibm-granite/granite.build, covering agents.md, git commits, github prs and issues, project overview and common commands.
ai-git-commiter CLAUDE.md
Instructions for zdt1013/ai-git-commiter, covering ai git commiter, 项目结构, 技术栈, 常用命令 and 安装依赖.