metrics

Metrics

Input: $ARGUMENTS = optional flags (--period <N>, --output <path>, --format <md|json|html>)

Flag parsing

FORMAT=""        # empty = no flag supplied = trigger interactive prompt path
PERIOD=30
OUTPUT=""
while [[ $# -gt 0 ]]; do
  case "$1" in
    --period)
      PERIOD="$2"; shift 2
      ;;
    --output)
      OUTPUT="$2"; shift 2
      ;;
    --format)
      FORMAT="$2"; shift 2
      [[ "$FORMAT" =~ ^(md|json|html)$ ]] || { echo "Error: --format must be 'md', 'json', or 'html'"; exit 1; }
      ;;
    *)
      shift
      ;;
  esac
done

# Sentinel for interactive-prompt path
NO_FORMAT_FLAG=0
if [ -z "$FORMAT" ]; then
  NO_FORMAT_FLAG=1
  FORMAT="md"   # default render is markdown; prompt fires AFTER render
fi

• --period N → period in days (default: 30)
• --output path → output file (default: stdout)
• --format md|json|html → output format (default: md with interactive prompt)

Configuration

Read Automation Config from CLAUDE.md section ## Automation Config:

• Issue Tracker: Type, Instance, Project, Bug query, State transitions
• Source Control: Remote
• Optionally: Feature Workflow → Feature query
• Optionally: Metrics → Output, Period (overrides defaults)

0. MCP pre-flight check

Before any pipeline operation, verify MCP tool availability:

• Read Type from Automation Config (Issue Tracker section)
• Check that at least one mcp__* tool matching the tracker type is accessible
• If not accessible → STOP with: "Cannot connect to your {Type} issue tracker. Is the {Type} integration configured? Run /agent-flow:check-setup for diagnostics."

Orchestration

1. Fetch issues

Via MCP server (per Issue Tracker → Type), fetch all issues matching Bug query + Feature query (if it exists). For each issue: ID, title, state, comments, created date.

2. Parse [agent-flow] comments

For each issue, go through comments. Extract:

Triage checkpoint: Regex: ^\[agent-flow\] Triage completed\. Severity: (.+)\. Area: (.+)\.$