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 report-debtgit 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/report-debt)<a href="https://agentmods.dev/skills/panbanda/omen/report-debt"><img src="https://agentmods.dev/badge/skills/panbanda/omen/report-debt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/panbanda/omen/report-debt"><img src="https://agentmods.dev/badge/skills/panbanda/omen/report-debt.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00992 |
| Opus 5.5 | $0.00013 | $0.00397 |
| Sonnet 5.5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
report-debt 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Debt
Generate a comprehensive technical debt assessment with quantified metrics, prioritized issues, and actionable recommendations.
Prerequisites
Omen CLI must be installed and available in PATH.
Workflow
Step 1: Scan for Self-Admitted Debt
Run the SATD analysis to find explicit debt markers:
omen -f json satd
Captures TODO, FIXME, HACK, XXX, and other debt markers with severity.
Step 2: Calculate TDG Scores
Run the TDG analysis for quality grades:
omen -f json tdg
TDG provides A-F grades based on complexity, churn, and health metrics.
Step 3: Measure Duplication
Run the clone detection analysis:
omen -f json clones
Calculate duplication ratio and identify clone clusters.
Step 4: Assess Defect Risk
Run the defect prediction analysis:
omen -f json defect
Identify files with high predicted defect probability.
Step 5: Check Complexity
Run the complexity analysis:
omen -f json complexity
Find functions exceeding complexity thresholds.
Debt Categories
Organize findings by category:
| Category | Source | Impact |
|---|---|---|
| Explicit | SATD markers | Known issues, documented |
| Structural | TDG grade D/F | Hard to maintain |
| Duplication | Clone ratio > 5% | Maintenance burden |
| Risk | Defect probability > 0.7 | Likely to cause bugs |
| Complexity | Cyclomatic > 15 | Hard to test/modify |
Output Format
Generate a stakeholder-ready report:
# Technical Debt Report
Generated: YYYY-MM-DD
## Executive Summary
| Metric | Value | Status |
|--------|-------|--------|
| Overall TDG Grade | C+ | Needs attention |
| Duplication Ratio | 7.2% | Above target (5%) |
| High-Risk Files | 12 | 8% of codebase |
| SATD Items | 45 | 12 critical |
## Debt by Category
### Explicit Debt (SATD)
- **Critical**: 12 items (FIXME, HACK)
- **High**: 18 items (TODO with urgency)
- **Normal**: 15 items (TODO)
Top items:
1. `payment/processor.go:45` - HACK: Temporary fix for race condition
2. `auth/session.go:123` - FIXME: Security review needed
3. ...
### Structural Debt (TDG Grades)
| Grade | Files | % of Codebase |
|-------|-------|---------------|
| A | 45 | 30% |
| B | 52 | 35% |
| C | 32 | 21% |
| D | 15 | 10% |
| F | 6 | 4% |
Worst files:
1. `legacy/importer.go` - Grade F (TDG: 18)
2. `core/processor.go` - Grade D (TDG: 35)
### Duplication Debt
- **Total clones**: 23 clone groups
- **Duplicated lines**: 1,245 (7.2% of codebase)
Largest clones:
1. 85 lines duplicated across 3 files in `handlers/`
2. 45 lines duplicated between `validator.go` and `checker.go`
### Risk Debt
- **High-risk files**: 12 (defect probability > 0.7)
- **Medium-risk files**: 28 (probability 0.5-0.7)
## Recommended Actions
### Sprint 1 (Quick Wins)
1. Address 12 critical SATD items (est: 8 hours)
2. Consolidate largest clone cluster (est: 4 hours)
3. Split `legacy/importer.go` (est: 6 hours)
### Sprint 2-3 (Structural)
1. Refactor Grade D files (est: 20 hours)
2. Reduce complexity in `core/processor.go` (est: 8 hours)
### Long Term
1. Eliminate all Grade F files
2. Reduce duplication to < 3%
3. Add tests to high-risk files
## Tracking
| Metric | Last Month | This Month | Trend |
|--------|------------|------------|-------|
| TDG Average | 62 | 58 | Improving |
| Duplication | 8.1% | 7.2% | Improving |
| SATD Critical | 15 | 12 | Improving |
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.
- 1mo ago First seen · 156 lines · 32 tokens per session scan A c6d9beb9f490
report-debt is a skill published in the GitHub repository panbanda/omen (21 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 992 once invoked, about $0.0001 per session on Opus 5.5. 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
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
memory-leak-debugging
Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to capture, compare, or inspect heap snapshots with Chrome DevTools MCP memory tools.