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/lufermalgo/ai-for-non-developers/claude-mdgit clone --depth 1 https://github.com/lufermalgo/ai-for-non-developersWrote 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/lufermalgo/ai-for-non-developers/claude-md)<a href="https://agentmods.dev/instructions/lufermalgo/ai-for-non-developers/claude-md"><img src="https://agentmods.dev/badge/instructions/lufermalgo/ai-for-non-developers/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 5.1 | $0.02193 | $0.02193 |
| Opus 5 | $0.01097 | $0.01097 |
| Sonnet 5 | $0.00439 | $0.00439 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
ai-for-non-developers CLAUDE.md 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 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.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI for Non-Developers — Agent Rules
1. Token Efficiency — The Fundamental Principle
- Read once: internalized at session start; never re-read during active work.
- Read before writing: inspect existing code before modifying. Never write blind.
- Edit, don't rewrite: targeted edits only. Full rewrites require explicit justification.
- No redundant reads: never re-read a file already loaded unless it may have changed.
- Surgical reads: only the file being edited, only relevant lines. No project-wide scans.
- Focused diffs: touch only what the task requires. Zero side edits.
- Lazy loading: pull context just-in-time, never preemptively.
- Platform capabilities: use available skills, MCP, plugins, hooks natively — never do manually what the platform can do.
- Skill management: use
aind skill listto browse the registry,aind skill add <name>to install into the project,aind skill remove <name>to uninstall. To create a new skill, installskill-creatorfirst (aind skill add skill-creator) then invoke it. Never write to global paths (~/.claude/) — skills are always project-scoped. - Subagents: use for exploration, research, parallel independent work — never for single-file edits. Select lightest capable model. Instructions must be self-contained, scoped, bounded — pass only relevant excerpts, never full files. Validate result; retry once with sharper prompt if wrong; handle inline if it fails twice.
- Archive: move stable specs to
specs/archive/immediately after feature stability. - Output: no greetings, preambles, or trailing narration. Default: one concise line.
2. Communication
- Plain language. No jargon. No filler. No greetings. No trailing summaries.
- Default output: one line. Expand to max 3 bullets only if outcome is non-obvious or human explicitly asks.
- Interact with human only for: spec validation, UX confirmation, token checkpoint.
- If blocked by business ambiguity: one precise question, nothing more.
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 · 131 lines · 2,193 tokens per session scan A 6878c1bda771
ai-for-non-developers CLAUDE.md is an instructions file published in the GitHub repository lufermalgo/ai-for-non-developers (1 stars, last pushed 4mo ago), licensed MIT. It adds 2,193 tokens to every session, about $0.0110 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
claude-mem copilot-instructions.md
Copilot instructions for thedotmack/claude-mem, a project described as: Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes…
relayBrain copilot-instructions.md
Instructions for prakrititz/relayBrain, covering relay (auto-installed) and relay pseudo-commands (user chat).
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.
cerebro-inevita CLAUDE.md
Claude Code instructions for gabrielzucco/cerebro-inevita, covering a unidade do cérebro: o átomo, engenharia de contexto — o método (4 movimentos), a estrutura (um protocolo, seis superfícies), como você opera (as skills e seus relógios) and regras (invioláveis).
gui_agent AGENTS.md
AGENTS.md instructions for leandre755/gui_agent, covering git-context-controller (gcc) protocol, 3.1. .gcc/main.md template, current project context, 🏆 major milestones (archived epics) and 🎯 objective.
Noshy AGENTS.md
Instructions for Noshkoto/Noshy, covering noshy — ai agent instructions, what noshy is, architecture principles, how to work on this codebase and what not to do.