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.
npx skills add panbanda/omen --skill track-trendsgit clone --depth 1 https://github.com/panbanda/omenWrote 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.
[](https://agentmods.dev/skills/panbanda/omen/track-trends)<a href="https://agentmods.dev/skills/panbanda/omen/track-trends"><img src="https://agentmods.dev/badge/skills/panbanda/omen/track-trends.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.01244 |
| Opus 5 | $0.00016 | $0.00622 |
| Sonnet 5 | $0.00006 | $0.00249 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
track-trends 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- results-writer — 86% identical, 209 lines differ
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Track Trends
Generate historical analysis of repository health metrics over time to identify improvement or degradation patterns.
Prerequisites
Omen CLI must be installed and available in PATH.
When to Use
- Quarterly engineering health reports
- Release retrospectives
- Tracking debt paydown initiatives
- Justifying refactoring investments with data
- Identifying gradual quality degradation
Workflow
Step 1: Run Trend Analysis
Use the Omen CLI to analyze historical scores:
# Last 3 months, weekly sampling (default)
omen score trend --since 3m
# Last 6 months for quarterly report
omen score trend --since 6m --period monthly
# Full year for annual review
omen score trend --since 1y --period monthly
Parameters:
--since: How far back to analyze (3m, 6m, 1y, 2y, 30d, 4w, all). Defaults toall(full history).--period: Sampling frequency (daily, weekly, monthly)
Step 2: Interpret Results
The output includes:
| Field | Meaning |
|---|---|
| Score | Composite health score (0-100) |
| Slope | Points gained/lost per period |
| R-squared | How consistent the trend is (0-1) |
| Correlation | Direction and strength (-1 to 1) |
Trend interpretation:
- Positive slope = improving health
- Negative slope = degrading health
- High R-squared (>0.7) = consistent trend
- Low R-squared (<0.3) = volatile/no clear trend
Step 3: Analyze Component Trends
Each component has its own trend statistics:
| Component | What It Measures |
|---|---|
| Complexity | Function complexity violations |
| Duplication | Code clone ratio |
| SATD | Self-admitted technical debt |
| TDG | Technical Debt Gradient |
| Coupling | Cyclic dependencies, instability |
| Smells | Architectural issues |
| Cohesion | Class cohesion (LCOM) |
Look for diverging trends - overall score improving but one component degrading.
Output Format
Generate a trend report:
# Repository Health Trend Report
Period: [Start Date] to [End Date]
## Executive Summary
| Metric | Start | End | Change | Trend |
|--------|-------|-----|--------|-------|
| Overall Score | 72 | 85 | +13 | Improving |
| Complexity | 68 | 91 | +23 | Strong improvement |
| Duplication | 75 | 66 | -9 | Degrading |
| SATD | 80 | 85 | +5 | Stable improvement |
| TDG | 82 | 88 | +6 | Improving |
| Coupling | 70 | 75 | +5 | Stable |
| Smells | 100 | 100 | 0 | Excellent |
| Cohesion | 95 | 100 | +5 | Excellent |
## Trend Analysis
**Overall trajectory:** Score improving at +2.1 points/month (R-squared: 0.89)
**Key observations:**
1. Complexity improved significantly after refactoring sprint in [month]
2. Duplication trending down - clone detection shows new patterns emerging
3. Technical debt (SATD) being addressed consistently
## Component Deep Dive
### Complexity (Strong Improvement)
- Started: 68 (15 functions over threshold)
- Current: 91 (3 functions over threshold)
- Key changes: Refactored payment processor, split auth handler
### Duplication (Concerning)
- Started: 75 (4.2% duplication)
- Current: 66 (6.1% duplication)
- Action needed: New handler patterns being copy-pasted
## Recommendations
### Immediate Actions
1. Address duplication in `handlers/` directory
2. Review new code for copy-paste patterns
### Next Quarter Goals
1. Maintain complexity below 5 violations
2. Reduce duplication back to <5%
3. Continue SATD remediation pace
## Historical Data Points
| Date | Commit | Score | Cx | Dup | SATD | TDG | Coup | Smell | Coh |
|------|--------|-------|-----|-----|------|-----|------|-------|-----|
| 2024-01 | abc123 | 72 | 68 | 75 | 80 | 82 | 70 | 100 | 95 |
| 2024-02 | def456 | 76 | 75 | 72 | 82 | 84 | 72 | 100 | 98 |
| 2024-03 | ghi789 | 85 | 91 | 66 | 85 | 88 | 75 | 100 | 100 |
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.
- 8d ago First seen · 172 lines · 32 tokens per session scan A a7732d45a7b1
track-trends is a skill published in the GitHub repository panbanda/omen (19 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,244 once invoked, about $0.0002 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.
Other skills, from other repositories
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…
issue-reporter
A tool for submitting a GitHub Issue, Bug Report, or Feature Request when the user explicitly asks for one. A GitHub Issue is a tracked report or request in a software project.
github-fix-issue
Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing a GitHub issue, says "fix issue.
memstack-security-git-guard
Use when the user says 'git-guard', 'check git protection', 'is this repo protected', 'verify gitleaks', 'set up git hooks', 'install git-guard', or wants to confirm a repo blocks secrets and internal files before commit. This is an installer and verifier, NOT a scanner (gitleaks does the actual scanning). Do NOT use…
polish-docs-meta
Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.