bug-council

bug-council is a command for coding agents from ushibo/brigade. It costs 28 tokens per session (1,383 once invoked), scanned A, original, MIT.

A diagnostic command that asks five specialist agents to investigate a difficult or recurring bug in parallel and combines their findings.

In plain words
What is it for?
It collects symptom and reproduction details, records a bug report, compares diagnostic analyses, and produces a root-cause and fix recommendation.
Why use it?
It brings multiple technical perspectives to bugs that have resisted repeated fixes or have several plausible causes.

Command

Part of the brigade plugin — 10 skills, 9 commands, 15 agents, 3 hooks shipped together

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/ushibo/brigade/bug-council
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade

Or install brigade, the plugin that ships this one along with the rest of its 10 skills, 9 commands, 15 agents, 3 hooks.

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 bug-council

README.md
[![agentmods](https://agentmods.dev/badge/commands/ushibo/brigade/bug-council.svg)](https://agentmods.dev/commands/ushibo/brigade/bug-council)
Your own site
<a href="https://agentmods.dev/commands/ushibo/brigade/bug-council"><img src="https://agentmods.dev/badge/commands/ushibo/brigade/bug-council.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,383 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 $0.00028 $0.01383
Opus 5 $0.00014 $0.00691
Sonnet 5 $0.00006 $0.00277
Haiku 4.5 $0.00003 $0.00138

Measured 3d ago against content hash a8654bcba0a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-council 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 3d 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.

commands/bug-council.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are convening a Bug Council — a team of 5 specialized diagnostic agents who analyze a hard bug from different angles in parallel, then you synthesize their findings into a single root cause and fix recommendation.

When to use

  • /brigade:fix failed 3+ times on the same bug
  • A bug has been fought for an hour+ with no clear root cause
  • A bug appears to have multiple possible causes
  • A bug keeps coming back after being "fixed"
  • You can't reproduce consistently and need multiple perspectives

Do NOT use for simple bugs — /brigade:fix is faster and cheaper.

Preflight

  1. Verify the working tree is clean OR the user confirms the current state is expected.
  2. Verify .planning/tasks/ROLES.md exists (not strictly required, but helps diagnostics).
  3. Create .planning/bug-council/ directory if missing.

Step 1 — Capture the bug report

Read $ARGUMENTS. If it's vague, ask the user ONCE for:

  • What's the symptom? (error message, unexpected behavior, failing test)
  • How to reproduce?
  • Which files do you suspect? (optional)

Write a brief bug report to .planning/bug-council/{timestamp}-bug.md:

# Bug report

**Date:** {date}
**Symptom:** {what's broken}
**Reproduction:** {steps}
**Suspect files:** {if known}
**Previous fix attempts:** {if any — what was tried, what failed}

Step 2 — Spawn all 5 diagnostic agents in parallel

CRITICAL: emit all 5 Agent calls in a SINGLE message. Parallelism only works when all calls are in the same assistant response.

Each agent gets the same bug report and a role-specific prompt. All 5 write their reports to distinct files under .planning/bug-council/{timestamp}/.

Agent Report file Focus
root-cause-analyst root-cause.md 4-phase debugging, trace to source
code-archaeologist archaeology.md git history, when was this introduced
pattern-matcher patterns.md similar bugs elsewhere, working examples
systems-thinker systems.md coupling, data flow, invariants
adversarial-tester adversarial.md edge cases, assumptions that might break

Read the full file on GitHub · 165 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. 3d ago First seen · 165 lines · 28 tokens per session scan A a8654bcba0a4

Subscribe to this mod's changes

bug-council is a command published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,383 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 2026-08-31.