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 stilero/claude-plugins --skill tech-debt-auditgit clone --depth 1 https://github.com/stilero/claude-pluginsWrote 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/stilero/claude-plugins/tech-debt-audit)<a href="https://agentmods.dev/skills/stilero/claude-plugins/tech-debt-audit"><img src="https://agentmods.dev/badge/skills/stilero/claude-plugins/tech-debt-audit.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 | $0.00101 | $0.00627 |
| Opus 5 | $0.00051 | $0.00313 |
| Sonnet 5 | $0.00020 | $0.00125 |
| Haiku 4.5 | $0.00010 | $0.00063 |
Grade A, and why
tech-debt-audit 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 6d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Debt Audit
This skill runs a comprehensive technical debt audit by spawning 11 specialized agents in parallel, each examining the codebase from a different angle.
How It Works
- Context gathering — reads CLAUDE.md, package.json, tsconfig.json, file tree, and git churn to understand the project
- Parallel audit — launches 11 agents simultaneously, each focused on one category of technical debt
- Aggregation — merges findings, deduplicates overlapping issues, boosts severity when multiple agents converge
- Report — presents grouped issues ranked by severity
- Issue creation — offers to create GitHub issues for selected findings
The 11 Audit Agents
| Agent | Focus | Model |
|---|---|---|
| dependency-auditor | Outdated deps, CVEs, unused packages | haiku |
| code-quality-analyzer | Code smells, complexity, duplication, dead code | sonnet |
| architecture-reviewer | Circular deps, layer violations, pattern inconsistencies | sonnet |
| test-coverage-analyzer | Untested modules, test quality, integration gaps | sonnet |
| error-handling-auditor | Swallowed errors, missing error handling, resilience | sonnet |
| performance-analyzer | N+1 queries, missing indexes, unbounded queries | sonnet |
| security-scanner | Secrets, injection, validation, auth gaps | sonnet |
| documentation-auditor | Missing API docs, stale docs, missing ADRs | haiku |
| type-safety-auditor | any usage, unsafe assertions, strict mode gaps | sonnet |
| api-design-reviewer | Endpoint naming, pagination, error consistency | sonnet |
| complexity-reviewer | Over-engineering, unnecessary abstractions, YAGNI | sonnet |
Severity Boosting
When multiple agents flag the same area or pattern, severity is bumped one level:
- An issue found by 1 agent keeps its original severity
- An issue found by 2+ agents gets bumped (LOW→MEDIUM, MEDIUM→HIGH, HIGH→CRITICAL)
Issue Grouping
Related findings are merged into single actionable issues:
- 8 endpoints missing pagination → one issue
- 15 files using
anytype → one issue - 3 circular dependency chains → one issue
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.
- 6d ago First seen · 50 lines · 101 tokens per session scan A 23a054a2b919
tech-debt-audit is a skill published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 627 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.