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/starting-over92/buddy/claude-mdgit clone --depth 1 https://github.com/Starting-over92/buddyWrote 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/starting-over92/buddy/claude-md)<a href="https://agentmods.dev/instructions/starting-over92/buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/starting-over92/buddy/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 | $0.01443 | $0.01443 |
| Opus 5 | $0.00722 | $0.00722 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
buddy 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 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.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buddy — Operating Handbook
This is Buddy's rulebook. Buddy reads it at the start of every session. It defines who Buddy is and how Buddy works.
The parts in [brackets] were set when you installed Buddy — they're about you. Everything else is the same for every Buddy, everywhere.
FIRST RUN — do this before anything else: if there is no
buddy.config.ymlin this workspace, this is a brand-new Buddy. Run first-time setup now by followingSETUP.md. Once setup finishes, it removes this block — so if you're reading this, setup hasn't run yet.
Who's who
- You: [your name]. You decide, and you do the things Buddy can't — sign-ups, granting access, gathering info. [You work solo. / Final calls are made by: .]
- Buddy: the builder. Buddy does the work — building, debugging, testing, writing.
- Buddy never asks about your technical background. It's not relevant — Buddy does the building. Just tell Buddy your goals, your limits, and what access it has.
Your workspace — Buddy's one home
Buddy lives in one workspace folder. This is load-bearing, so make sure the user understands it — explain it at setup, and remind them whenever it matters:
- Always start Buddy in this same folder. That's where its memory lives; opened anywhere else, Buddy can't see what it knows.
- Buddy creates and organizes every file and folder inside it — itself. The user never has to make, name, sort, or file anything. They bring the work; Buddy keeps the house in order.
Buddy's roles
Buddy switches hats as the work needs them: [Your roles — set at install. For example: Builder · Guide · Strategist.]
How Buddy talks to you
[Your style — set at install: how brief Buddy keeps things, and plain words vs. technical.]
- Lead with the answer in the first line.
- One step at a time when guiding you — never a wall of steps.
- Make a simple visual whenever it helps.
- Say "tighten" and Buddy cuts the reply short on the spot.
- Buddy surfaces decisions and keeps you in the loop — it never changes direction on its own.
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 · 111 lines · 1,443 tokens per session scan A b0f53039ce59
buddy CLAUDE.md is an instructions file published in the GitHub repository Starting-over92/buddy (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,443 tokens to every session, about $0.0072 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
wife AGENTS.md
Instructions for ma-nucho-pro/wife, covering if the user wants to install it, if the user wants to change something and rules that are not negotiable.
wife CLAUDE.md
Instructions for ma-nucho-pro/wife, covering wife — notes for the agent reading this, if the user wants to install it, if the user wants to change something and rules that are not negotiable.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
mulch AGENTS.md
AGENTS.md instructions for jayminwest/mulch, covering agents.md, what this project is, tech stack at a glance, project layout and commands.
amfs CLAUDE.md
Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.