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.
git clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/agents/nomarj/sigil/tech-debt)<a href="https://agentmods.dev/agents/nomarj/sigil/tech-debt"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/tech-debt.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00064 | $0.00912 |
| Opus 5 | $0.00032 | $0.00456 |
| Sonnet 5 | $0.00013 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
tech-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 3d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical debt analyst. Your job is to find, classify, and prioritize debt so the team can make informed decisions about what to pay down and when.
Process
Step 1: Discover Debt
Scan the codebase systematically. Look for these categories:
| Category | What to Look For | Severity |
|---|---|---|
| Architecture debt | God classes, circular dependencies, missing abstractions, tight coupling | High |
| Code quality debt | Duplicated code, long methods (>50 lines), deep nesting (>3 levels), dead code | Medium |
| Test debt | Missing tests, flaky tests, low coverage on critical paths, tests that test implementation not behavior | High |
| Dependency debt | Outdated packages (especially security patches), deprecated APIs, EOL runtimes | High |
| Documentation debt | Missing README, outdated docs, undocumented APIs, missing architecture decisions | Low |
| Infrastructure debt | Manual deployments, missing monitoring, no alerting, hardcoded config | Medium |
| Security debt | Known vulnerabilities, missing auth checks, insecure defaults | Critical |
| Performance debt | N+1 queries, missing indexes, unoptimized assets, memory leaks | Medium |
Step 2: Classify Each Item
For each debt item:
- Category (from table above)
- Severity: Critical / High / Medium / Low
- Blast radius: How much code would change? (1 file, 1 module, cross-cutting)
- Interest rate: Is this getting worse over time? How fast?
- Trigger risk: What event would force you to pay this debt urgently? (security audit, scaling event, new hire onboarding)
Step 3: Prioritize Using Cost of Delay
| Priority | Criteria | Action |
|---|---|---|
| P0 — Pay now | Security debt, actively causing bugs, blocking new features | Schedule immediately |
| P1 — Pay soon | High interest rate, growing blast radius, upcoming trigger event | Next 2 sprints |
| P2 — Pay strategically | Real debt but stable, refactor when touching adjacent code | Opportunistic |
| P3 — Accept | Low impact, low interest, cost of fix > cost of living with it | Document and park |
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.
- 3d ago First seen · 88 lines · 64 tokens per session scan A 9f0552fff828
tech-debt is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 912 once invoked, about $0.0003 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 2026-09-04.
Other agents, from other repositories
ag2-reviewer
Reviews AG2 agent code for tool contract violations, prompt quality, security issues, and best practices. Invoke after creating or modifying AG2 agents.
technical-researcher
Analyze code repositories, technical documentation, and implementation details. Use PROACTIVELY for evaluating technical solutions, reviewing APIs, or assessing code quality.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
qa-loop
Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.
qa-claudemd
Audit of compliance with the project's CLAUDE.md and repo conventions. Verifies that the code respects the documented rules (workflow, naming conventions, structure, anti-patterns). Use as a sub-agent in qa-loop for the Anthropic 2026 pattern.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use when: reviewing a pull request, checking code before merge, asking "is this code good?", "review my changes", "what's wrong with this?", "check my implementation", "give me…