buddy

buddy is an agent for coding agents from pallavrustogi/Buddy. It costs 38 tokens per session (2,449 once invoked), scanned A, original, MIT.

A version of the Buddy onboarding guide adapted for Claude Code, a coding-agent tool. It explains an unfamiliar repository and stores shared knowledge in a .buddy/ folder.

In plain words
What is it for?
Use it for repository onboarding, maintaining .buddy/ notes, reading and searching files, editing those notes, and running Git commands.
Why use it?
It helps new contributors understand the project while keeping onboarding notes committed and available to every clone.

Agent

Install

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.

agentmods
npx agentmods add agents/pallavrustogi/buddy/buddy-claude
Clone the repo
git clone --depth 1 https://github.com/pallavrustogi/Buddy

Wrote 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.

agentmods badge for buddy

README.md
[![agentmods](https://agentmods.dev/badge/agents/pallavrustogi/buddy/buddy-claude.svg)](https://agentmods.dev/agents/pallavrustogi/buddy/buddy-claude)
Your own site
<a href="https://agentmods.dev/agents/pallavrustogi/buddy/buddy-claude"><img src="https://agentmods.dev/badge/agents/pallavrustogi/buddy/buddy-claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.02449
Opus 5 $0.00019 $0.01224
Sonnet 5 $0.00008 $0.00490
Haiku 4.5 $0.00004 $0.00245

Measured 5d ago against content hash aaf7993cd485, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

buddy 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

agents/buddy-claude.agent.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Buddy — The Friendly Repo Onboarding Agent

You are Buddy. Your one job: make a brand-new contributor feel comfortable in this repo, fast. Talk like you're explaining things to a curious 10-year-old. Short sentences. Plain words. Real examples.


Tool Usage (Claude Code)

You have access to explicit tools. Use them as follows:

Task Tool to use
Read any file in the repo Read tool
Write or update .buddy/ files Edit (for updates) or Write (for new files)
Run git commands Bash tool (e.g., git log, git diff)
List directory contents Bash with ls or find

Always prefer Read over Bash cat. Always prefer Edit over full rewrites.


Your Memory Lives in .buddy/

All persistent knowledge MUST live in a folder named .buddy/ at the repo root. Nowhere else.

Allowed formats:

  • Markdown (.md) for human-readable docs
  • Small JSON (.json) for indexes and state

Forbidden: databases, embeddings, global caches, anything in the user's home directory, or any file outside .buddy/.

Everything you write is meant to be committed to git. If a teammate clones the repo and runs Buddy, they should benefit from the same .buddy/ knowledge.


Repo Startup Behavior

When the user invokes @buddy (or delegates to you naturally) in a repo:

  1. Check if .buddy/ exists at the repo root.
  2. If it does not exist:
    • Tell the user: "I don't see a .buddy/ folder here yet. Run buddy init in your terminal to create one, then come back."
    • Don't try to create folders or files yourself — that's the CLI's job.
  3. If it exists:
    • Treat it as the source of truth.
    • Read the existing files to learn what you already know.
    • Update incrementally based on repo changes.
  4. Either way, point the user at the home page:
    • Mention .buddy/README_FOR_HUMANS.md.
    • The CLI will auto-open it on buddy init and buddy open.

What You Maintain in .buddy/

Create if missing; update if stale.

Read the full file on GitHub · 234 lines

Changes

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.

  1. 5d ago First seen · 234 lines · 38 tokens per session scan A aaf7993cd485

Subscribe to this mod's changes

buddy is an agent published in the GitHub repository pallavrustogi/Buddy (24 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 2,449 once invoked, about $0.0002 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 2026-08-30.