buddy

A project-status command that shows the technology used, recent Git activity, working-tree changes, suggested agents, and next actions. Git is a tool for tracking code changes.

In plain words
What is it for?
Use it for a quick overview of the current project and recommendations for the next coding step.
Why use it?
It gathers the project context in one place so you do not have to inspect configuration, commits, and changes separately.

Command

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 commands/jeremydev87/codingbuddy/buddy
Clone the repo
git clone --depth 1 https://github.com/JeremyDev87/codingbuddy
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 714 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 $0.00019 $0.00714
Opus 5 $0.00010 $0.00357
Sonnet 5 $0.00004 $0.00143
Haiku 4.5 $0.00002 $0.00071

Measured yesterday against content hash a47641270cb3, 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 yesterday.

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.

packages/claude-code-plugin/commands/buddy.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/buddy — On-Demand Buddy Interaction

Purpose

Instant project overview with agent recommendations and next-action guidance. Makes CodingBuddy feel like a living assistant you can check in with anytime.

Instructions

When the user invokes /buddy, perform the following steps in order:

Step 1: Show Buddy Banner

Display the CodingBuddy character greeting:

╭━━━╮
┃ ◕‿◕ ┃  Hey! I'm your CodingBuddy!
╰━┳━╯

Step 2: Project Scan

Use the get_project_config MCP tool to retrieve the current project configuration.

Display a compact status summary:

## 📊 Project Status

| Item | Value |
|------|-------|
| Tech Stack | [detected from config] |
| Language | [from config language setting] |
| Architecture | [from config] |

Step 3: Recent Activity

Check recent git activity to understand current work context:

git log --oneline -5
git status --short
git branch --show-current

Display:

## 📝 Recent Activity

Branch: [current branch]
Recent commits:
- [commit 1]
- [commit 2]
- [commit 3]

Working tree: [clean / N files modified]

Step 4: Agent Recommendations

Based on the project scan and recent activity, use the analyze_task MCP tool with a summary of the current context to get agent recommendations.

Display:

## 🤖 Recommended Agents

Based on your current work:
| Agent | Why |
|-------|-----|
| [Agent Name] | [Brief reason based on context] |
| [Agent Name] | [Brief reason based on context] |
| [Agent Name] | [Brief reason based on context] |

Step 5: Suggested Next Actions

Based on the project state, suggest 2-3 concrete next actions:

## 🎯 What's Next?

1. **[Action]** — [Brief description]
2. **[Action]** — [Brief description]
3. **[Action]** — [Brief description]

💡 Tip: Type `PLAN [task]` to start planning, or `AUTO [task]` for autonomous execution.

Step 6: Quick Actions Menu

## ⚡ Quick Actions

- `/codingbuddy:plan` — Start planning a new task
- `/codingbuddy:act` — Execute current plan
- `/codingbuddy:eval` — Evaluate recent implementation
- `/codingbuddy:auto` — Autonomous development cycle
- `/codingbuddy:checklist [domain]` — Generate quality checklist
- `/codingbuddy:buddy` — Show this status again

Read the full file on GitHub · 125 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. yesterday First seen · 125 lines · 19 tokens per session scan A a47641270cb3

Subscribe to this mod's changes

buddy is a command published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 714 once invoked, about $0.0001 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.