the-agency-starter: Command for Claude Code

.claude/commands/agency-bug.md

agency-bug is a command for Claude Code from the-agency-ai/the-agency-starter. It costs 0 tokens per session (378 once invoked), scanned A, original, MIT.

A command for quickly recording a bug in The Agency, a multi-agent development setup. It saves a supplied summary in a numbered Markdown file under the project's bug directory.

In plain words
What is it for?
Use /agency-bug followed by a short summary to create a dated bug record with status, ownership, workstream, and reproduction placeholders.
Why use it?
It captures a problem without interrupting the current work or requiring a full bug report immediately.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is the-agency-ai/the-agency-starter's own configuration. It tells Claude Code how to work on the-agency-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything the-agency-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to the-agency-ai/the-agency-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/the-agency-ai/the-agency-starter/main/.claude/commands/agency-bug.md
Clone the repo
git clone --depth 1 https://github.com/the-agency-ai/the-agency-starter

Made for: Claude Code.

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 agency-bug

README.md
[![agentmods](https://agentmods.dev/badge/commands/the-agency-ai/the-agency-starter/agency-bug/github.svg)](https://agentmods.dev/commands/the-agency-ai/the-agency-starter/agency-bug)
Your own site
<a href="https://agentmods.dev/commands/the-agency-ai/the-agency-starter/agency-bug"><img src="https://agentmods.dev/badge/commands/the-agency-ai/the-agency-starter/agency-bug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agency-bug

Your own site · 80×15
<a href="https://agentmods.dev/commands/the-agency-ai/the-agency-starter/agency-bug"><img src="https://agentmods.dev/badge/commands/the-agency-ai/the-agency-starter/agency-bug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 378 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00378
Opus 5 $0.00000 $0.00189
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured 12d ago against content hash 8888e9881f2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agency-bug 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 12d 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.

.claude/commands/agency-bug.md · 71 lines

What it actually says

Report a bug quickly

The user typed: /agency-bug $ARGUMENTS

Purpose: Quickly capture a bug without breaking the user's flow.

Behavior

  1. If $ARGUMENTS is empty, show usage:

    Usage: /agency-bug <summary>
    
    Example: /agency-bug Config tool outputs errors to stdout instead of stderr
    

    Then stop - do not prompt for input.

  2. If $ARGUMENTS is provided, use it as the bug summary

  3. Determine current agent context (default: housekeeping/captain)

  4. Create the bug file

  5. Confirm creation

Implementation

  1. Get the current date: date +%Y-%m-%d
  2. Find the next bug number by counting existing bugs in claude/workstreams/housekeeping/bugs/
  3. Create the bug file using the template below
  4. Output confirmation

Bug File Location

claude/workstreams/housekeeping/bugs/BUG-XXXX.md

Bug File Template

# BUG-XXXX: {Short summary from $ARGUMENTS}

**Status:** Open
**Reported:** {today's date}
**Assigned To:** captain
**Workstream:** housekeeping

## Description

{$ARGUMENTS}

## Steps to Reproduce

<!-- To be filled in -->

## Expected Behavior

<!-- To be filled in -->

Output Format

After creating the bug:

Bug captured: BUG-XXXX
Assigned to: housekeeping/captain
Description: {first 60 chars of summary}...

Notes

  • Keep it fast - don't ask unnecessary questions
  • Default to housekeeping/captain for now
  • Bug numbers are zero-padded to 4 digits (BUG-0001, BUG-0042)
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. 12d ago First seen · 71 lines · 0 tokens per session scan A 8888e9881f2b

Subscribe to this mod's changes

agency-bug is a command published in the GitHub repository the-agency-ai/the-agency-starter (20 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 378 tokens. 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.