devteam-bug
Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.
Display system health, current progress, costs, and execution history.
$ npx -y skills add michael-harris/devteam --skill devteam-status --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/devteam-statusContext preview
The summary Claude sees to decide when to auto-load this skill.
Display system health, current progress, costs, and execution history.
name: devteam-status description: Display system health, current progress, costs, and execution history. argument-hint: [--history [n]] [--costs] [--detailed] [--agents] [--session <id>] [--all] [--json] user-invocable: true allowed-tools: Read, Glob, Grep, Bash model: haiku
Session state: !`source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_current_session 2>/dev/null || echo "No active session"` Recent events: !`sqlite3 .devteam/devteam.db "SELECT type, message FROM events ORDER BY created_at DESC LIMIT 10" 2>/dev/null || echo "No events"`
**Command:** `/devteam:status [options]`
Display system health, current progress, costs, and execution history.
# Current session status /devteam:status # Show execution history /devteam:status --history /devteam:status --history 20 # Last 20 sessions # Cost breakdown /devteam:status --costs /devteam:status --costs --detailed # Agent performance metrics /devteam:status --agents # Check specific session /devteam:status --session session-20260129-123456-abc123 # Show all (comprehensive report) /devteam:status --all
| Option | Description | |--------|-------------| | `--history [n]` | Show last n sessions (default: 10) | | `--costs` | Show cost breakdown | | `--detailed` | Show detailed breakdown (with --costs) | | `--agents` | Show agent performance metrics | | `--session <id>` | Show specific session details | | `--all` | Show comprehensive report | | `--json` | Output as JSON |
source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh"
if is_session_running; then
show_current_session_status
else
show_system_overview
fiDevTeam Status
Session: session-20260129-103045-a1b2c3
Started: 2026-01-29 10:30:45 (23 min ago)
Command: /devteam:implement --sprint 1
Progress
Sprint: SPRINT-001 (Add user authentication)
Tasks: 60% (3/5 complete)
Current Task: TASK-004 - Implement JWT middleware
Agent: backend:api-developer-typescript
Model: sonnet (escalated from haiku)
Iteration: 3 of 10
Model Usage
Model | Runs | Success | Tokens | Cost
haiku | 12 | 83% | 45,231 | $0.06
sonnet | 4 | 75% | 28,102 | $0.42
opus | 1 | 100% | 15,883 | $2.38
Total | 17 | 82% | 89,216 | $2.86
Quality Gates (Last Iteration)
Lint passed
Type Check passed
Tests 2 failing (AuthMiddleware.test.ts)
Security pending
Coverage pending
Escalations
10:35 haiku -> sonnet 2 test failures (api_developer)
10:48 sonnet -> opus Architecture issue detected
Total: 2 escalations
Circuit Breaker
State: CLOSED (healthy)
Consecutive Failures: 1 of 5
Bug Council: Not activatedDevTeam Status
Status: Idle (no active session)
Recent Sessions
Session | Command | Status | Cost
session-20260129-093012-xxx | /devteam:bug | done | $1.24
session-20260128-161532-xxx | /devteam:impl... | done | $4.82
session-20260128-142201-xxx | /devteam:impl... | fail | $2.11
session-20260128-103045-xxx | /devteam:plan | done | $0.38
Active Plans
# | Plan | Status | Progress
1 | user-authentication | in_progress | 80%
2 | dark-mode-feature | ready | 0%
Lifetime Statistics
Total Sessions: 47
Success Rate: 89%
Total Cost: $127.43
Avg Cost/Session: $2.71
Most Used Agents:
1. backend:api-developer-typescript (142 runs, 91% success)
2. quality:test-writer (98 runs, 87% success)
3. frontend:developer (76 runs, 88% success)
Bug Council Activations: 3
Avg Escalations/Session: 1.2
Tip: Use /devteam:implement to start a new sessionDevTeam Cost Report Period: Last 30 days Cost by Model haiku $12.43 (10%) sonnet $68.21 (54%) opus $46.79 (36%) Total: $127.43 Cost by Command Type implement $89.21 (70%) bug $24.33 (19%) plan $10.12 (8%) issue $3.77 (3%) Cost by Agent (Top 10) Agent | Runs | Cost | Avg/Run backend:api-developer-typescript | 142 | $34.21 | $0.24 quality:test-writer | 98 | $18.43 | $0.19 quality:security-auditor | 23 | $15.82 | $0.69 frontend:developer | 76 | $12.11 | $0.16 bug_council (combined) | 3 | $11.24 | $3.75 ... Eco Mode Savings Sessions with --eco: 12 Estimated savings: $18.32 (23% reduction) Recommendation: Use --eco for routine tasks to save costs
Agent Performance Report
Agent Success Rates
Agent | Runs | Success | Avg Time
backend:api-developer-typescript | 142 | 91% | 2.3 min
backend:api-developer-python | 67 | 89% | 2.1 min
frontend:developer | 76 | 88% | 3.1 min
quality:test-writer | 98 | 87% | 1.8 min
quality:security-auditor | 23 | 96% | 4.2 min
diagnosis:root-cause-analyst | 15 | 80% | 3.5 min
Common Failure Reasons
Reason | Count | Usually Resolved By
Test failures | 34 | Model escalation
Type errors | 21 | Same model retry
Lint errors | 12 | Same model retry
Integration issues | 8 | Bug Council
Scope violation | 5 | Scope clarification
Escalation Patterns
haiku -> sonnet: 67 times (avg after 1.8 failures)
sonnet -> opus: 23 times (avg after 2.1 failures)
opus -> council: 3 times (avg after 2.7 failures)
Most escalated tasks:
- Security fixes (78% escalation rate)
- Architecture changes (65% escalation rate)
- Complex integrations (52% escalation rate)###
A Claude Code plugin providing 127 specialized AI agents with: Interview-driven planning - Clarify requirements before work begins Codebase research - Investigate patterns and blockers before implementation SQLite state management - Reliable session tracking
Repo: michael-harris/devteam
Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.
Detect design inconsistencies and drift from the design system. Launches the Design Drift Detector to analyze the codebase for deviations.
Coordinate UX/UI design work across platforms. Launches the UX System Coordinator to orchestrate design specialists.
Execute implementation work - plans, sprints, tasks, or ad-hoc work.