devteam-bug

A structured workflow for diagnosing and fixing software bugs, with an interview to gather missing details and a Bug Council for complex problems.

In plain words
What is it for?
Use it to fix bugs by describing the problem, setting severity or scope, answering follow-up questions, or requesting the council review.
Why use it?
It brings incomplete bug reports into a consistent process and adds a broader review when an issue needs more investigation.

Skill for Claude CodeCodex

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 skills/michael-harris/devteam/devteam-bug
Any agent
npx skills add michael-harris/devteam --skill devteam-bug
Clone the repo
git clone --depth 1 https://github.com/michael-harris/devteam

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,020 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 $0.00025 $0.03020
Opus 5 $0.00013 $0.01510
Sonnet 5 $0.00005 $0.00604
Haiku 4.5 $0.00003 $0.00302

Measured yesterday against content hash 759284147303, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devteam-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 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.

skills/devteam-bug/SKILL.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Current session: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_current_session 2>/dev/null || echo "No active session" Active sprint: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "active_sprint" 2>/dev/null || echo "None" Failure count: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "consecutive_failures" 2>/dev/null || echo "0"

DevTeam Bug Command

Command: /devteam:bug "<description>" [options]

Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.

Usage

# Basic bug fix (will trigger interview for missing details)
/devteam:bug "Login fails for guest users"

# Force Bug Council activation
/devteam:bug "Memory leak in image processor" --council

# Specify severity
/devteam:bug "Payment processing timeout" --severity critical
/devteam:bug "Button color wrong" --severity low

# Limit scope
/devteam:bug "API returns 500" --scope "src/api/"

# Skip interview (if you have all details)
/devteam:bug "Null pointer in UserService.getProfile() when user.settings is undefined" --skip-interview

# Cost-optimized
/devteam:bug "Minor typo in error message" --eco

Options

Option Description
--council Force Bug Council activation
--severity <level> Set severity: critical, high, medium, low
--scope <path> Limit search to specific files/directories
--skip-interview Skip clarifying questions
--eco Cost-optimized execution
--model <model> Force starting model

Your Process

Phase 0: Initialize Session

source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh"
source "${CLAUDE_PLUGIN_ROOT}/scripts/events.sh"

SESSION_ID=$(start_session "/devteam:bug \"$1\"" "bug")
log_session_started "/devteam:bug \"$1\"" "bug"
set_phase "interview"

Phase 1: Interview (Clarify Bug Details)

Always ask if missing from description:

bug_interview:
  required:
    - key: expected_behavior
      question: "What is the expected behavior?"
      skip_if: description contains "should" or "expected"

    - key: actual_behavior
      question: "What is the actual behavior?"
      skip_if: description contains "but" or "instead" or "actually"

  conditional:
    - key: repro_steps
      condition: description lacks step-by-step
      question: "What steps reproduce this issue?"

    - key: environment
      condition: could be environment-specific
      question: "What environment does this occur in? (browser, OS, version)"

    - key: frequency
      condition: not clear if consistent
      question: "Does this happen every time or intermittently?"

    - key: recent_changes
      condition: could be regression
      question: "Did this start recently? Any recent changes that might be related?"

    - key: error_message
      condition: no error mentioned
      question: "Are there any error messages or stack traces?"

Read the full file on GitHub · 488 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 · 488 lines · 0 tokens per session scan A 759284147303

Subscribe to this mod's changes

devteam-bug is a skill published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 3,020 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.

Related

Other skills, from other repositories

hydra

Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku, Sonnet) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code…

AR6420/Hail_Hydra · 83 tokens

quality-stack

Scan a project to detect configured quality and testing tools across JVM (Gradle/Maven), Android (AGP/Compose/KMP), Node.js/TypeScript, and Python ecosystems. Cross-reference against research-backed recommendations and assist with setup. Auto-detects project type(s) including monorepos with mixed ecosystems. Use when…

joaquimscosta/arkhe-claude-plugins · 148 tokens

prototype

Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to…

joaquimscosta/arkhe-claude-plugins · 118 tokens

lyra

Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

joaquimscosta/arkhe-claude-plugins · 56 tokens

taskfile-setup

Install Taskfile (task) and scaffold or audit Taskfile.yml configurations with ecosystem-aware templates. Auto-detects Node.js/pnpm, JVM/Gradle, Python/uv, Docker, and recommends single-file or multi-file (includes) patterns based on project complexity. Use when user runs /devtools:taskfile-setup, mentions "taskfile…

joaquimscosta/arkhe-claude-plugins · 110 tokens

sops-add-key

Add a new machine's age public key to .sops.yaml and re-encrypt all files. Use for multi-machine setups. Use when user mentions "add key", "add machine", "sops add key", "new machine", "authorize machine", "share key", "add public key", "multi machine sops".

joaquimscosta/arkhe-claude-plugins · 72 tokens