OrodruinLabs/nazgul:metrics
skills/metrics/SKILL.md
View loop performance metrics — task velocity, approval rates, retry distribution, reviewer stats. Use when asked about loop performance, development metrics, or how the loop is doing.
$ install --global
skillsauthnpx skillsauth add OrodruinLabs/nazgul nazgul:metricsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 5, 2026, 2:34 AM150.3s1 file scanned
SKILL.md
- name:
- nazgul:metrics
- description:
- View loop performance metrics — task velocity, approval rates, retry distribution, reviewer stats. Use when asked about loop performance, development metrics, or how the loop is doing.
- context:
- fork
- allowed-tools:
- Read, Bash, Glob, Grep
- author:
- Jose Mejia
- version:
- 1.3.2
Nazgul Metrics
Examples
/nazgul:metrics— View full metrics dashboard/nazgul:metrics reviews— Focus on reviewer stats
Current State
- Config: !
cat nazgul/config.json 2>/dev/null | head -3 || echo "NOT_INITIALIZED" - Tasks dir: !
ls nazgul/tasks/TASK-*.md 2>/dev/null | wc -l | tr -d ' ' - Checkpoints dir: !
ls nazgul/checkpoints/iteration-*.json 2>/dev/null | wc -l | tr -d ' ' - Reviews dir: !
ls -d nazgul/reviews/TASK-*/ 2>/dev/null | wc -l | tr -d ' '
Arguments
$ARGUMENTS
Instructions
Format all output per references/ui-brand.md — use stage banners, status symbols, progress bars, and display patterns defined there.
If Nazgul is not initialized, say so and stop.
Collect Data
Read these sources to compute metrics:
-
Task manifests (
nazgul/tasks/TASK-*.md):- Count by status: DONE, APPROVED, IN_PROGRESS, READY, CHANGES_REQUESTED, BLOCKED, PLANNED
- For each task: count retry attempts (how many times status went to CHANGES_REQUESTED)
- Extract claimed_at and completed_at timestamps for velocity
-
Checkpoints (
nazgul/checkpoints/iteration-*.json):- Total iterations run
- First and last iteration timestamps (for time span)
- Compaction count
-
Review files (
nazgul/reviews/TASK-*/):- For each task reviewed: count reviewer verdicts (APPROVED vs CHANGES_REQUESTED)
- Per-reviewer stats: how many times each reviewer approved vs rejected
- Consolidated feedback files: count blocking vs non-blocking findings
-
Config (
nazgul/config.json):- Mode, max iterations, consecutive failures
- Active reviewers list
Compute Metrics
- Task velocity: tasks DONE / total iterations (tasks per iteration)
- First-pass approval rate: tasks approved on first review / total reviewed tasks
- Retry distribution: histogram of retry counts (0, 1, 2, 3)
- Reviewer blocking rate: per reviewer, rejections / total reviews
- Avg iterations per task: total iterations / tasks DONE
- Time span: first checkpoint timestamp to last
- Loop health: consecutive failures, compaction count, active task status
Display Format
─── ◈ NAZGUL ▸ METRICS ─────────────────────────────────
Objective: [truncated to 80 chars]
Time span: [first timestamp] → [last timestamp]
Iterations: [total] ([compactions] compactions)
Task Velocity
─────────────────────────────────────
Total tasks: [N]
Completed: [N] ████████████░░░░ [%]
Tasks/iteration: [N.N]
Avg iters/task: [N.N]
Approval Rate
─────────────────────────────────────
First-pass approvals: [N]/[total] ([%])
Retry distribution:
0 retries: [N] tasks ████████████████
1 retry: [N] tasks ████████
2 retries: [N] tasks ████
3 retries: [N] tasks ██
Reviewer Stats
─────────────────────────────────────
[reviewer-name] ✦ [N] approved ✗ [N] rejected ([N]% block rate)
[reviewer-name] ✦ [N] approved ✗ [N] rejected ([N]% block rate)
...
Loop Health
─────────────────────────────────────
Consecutive failures: [N]
Mode: [hitl/afk]
Status: [active/paused/complete]
────────────────────────────────────────────────────────
If specific data is missing (no checkpoints, no reviews yet), show "No data" for that section rather than erroring.
Related Skills
OrodruinLabs/nazgul:verify
testing
VerifiedTrustedCommunity
Human acceptance testing — structured verification that work actually works. Run standalone or integrated in HITL review cycle.
4SKILL.mdUpdated Apr 23, 2026
OrodruinLabs/nazgul:task
devops
VerifiedTrustedCommunity
Task lifecycle management — skip, unblock, add, prioritize, info, and list tasks. Use when you need to manage individual tasks in the Nazgul pipeline.
4SKILL.mdUpdated Apr 23, 2026
OrodruinLabs/nazgul:status
development
VerifiedTrustedCommunity
Check the current state of a Nazgul autonomous loop. Use when asked about loop progress, task status, iteration count, review board status, or how the Nazgul loop is going.
4SKILL.mdUpdated Apr 23, 2026
OrodruinLabs/nazgul:start
development
VerifiedTrustedCommunity
Start or resume a Nazgul autonomous development loop. Use when user says "start nazgul", "run nazgul", "begin development", "resume the loop", or passes an objective for new work. Auto-detects project state — no arguments needed.
4SKILL.mdUpdated Apr 23, 2026