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 slbug/claude-ruby-grape-rails --skill techdebtgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWrote 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/slbug/claude-ruby-grape-rails/techdebt)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/techdebt"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/techdebt/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/slbug/claude-ruby-grape-rails/techdebt"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/techdebt.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 | $0.00055 | $0.01342 |
| Opus 5 | $0.00028 | $0.00671 |
| Sonnet 5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
rb:techdebt 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Debt
Read-only scan that logs tech-debt items and routes fixes to other commands. Never applies fixes itself.
Iron Laws
- Read-only scan; never auto-apply fixes.
- Multi-fix findings route to
/rb:plan; one-line fixes route to/rb:quick. - Architectural debt routes to
/rb:boundaries; whole-codebase context routes to/rb:audit. - Each finding records evidence (path:line, count, ripgrep snippet) — never opinion alone.
Debt Categories
| Category | Detection signal | Severity |
|---|---|---|
| Callback sprawl | after_* count per model > 5; cross-model callbacks |
Warning |
| Query repetition | Same where(...).order(...) pattern in 3+ places |
Warning |
| Oversized service objects | Service > 200 lines OR 5+ public methods | Critical |
| Decorative abstractions | Wrapper classes adding zero behavior | Info |
| Missing tests around legacy seams | Public method with 0 spec coverage in lib/legacy/ or untouched modules |
Critical |
| Dead code | Constants/methods with 0 references in repo (exclude fixtures) | Info |
| Controller bloat | Controller > 150 lines OR 7+ actions | Warning |
| Model bloat | Model > 300 lines OR 10+ scopes/associations | Warning |
| N+1 patterns at scale | .each { ... .association } in serializers |
Critical |
| Stale gem dependencies | Gemfile entries pinned 2+ years stale | Warning |
| Duplicate config sources | Same setting in application.rb + initializers/*.rb + .env |
Info |
| Unused gems | Gemfile entry with 0 require references | Info |
Detection commands per category live in references/:
references/callback-sprawl.mdreferences/service-bloat.mdreferences/dead-code-scan.md
Scan Procedure
- Identify scope. Whole repo / single package / single subsystem path. Default = current package boundary inferred from
Gemfile,packwerk.yml, orapp/packages/. - Per-category scan. Walk the Debt Categories table; for each row, run the detection signal:
wc -l,find -name '*.rb',rg --countfor size/count thresholds.rg --no-headingfor pattern presence.bundle outdated,bundle list --pathsfor gem staleness. Skip categories already known stable for the package.
- Score each finding. Assign severity tier (Critical / Warning / Info) per the table. Estimate fix-effort: small (<30 min), medium (1-4 h), large (>4 h).
- Record evidence per finding. Every entry MUST carry path:line, raw command output snippet, or count. Never opinion alone.
- Write artifact. Append one YAML block per finding to
.claude/audit/techdebt/{datesuffix}.mdusing the output template below. - Route findings. Multi-fix →
/rb:plan; one-liner →/rb:quick; architectural / boundary →/rb:boundaries; if scope crosses packages →/rb:audit. - Stop. Never apply fixes inline. Hand off to the chosen routing command.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 118 lines · 55 tokens per session scan A 92eb5889ba41
rb:techdebt is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,342 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 2026-09-03.
Other skills, from other repositories
kiss-dry-yagni
Principes KISS, DRY, YAGNI. Use when reviewing code quality or refactoring.
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
ia-verification-before-completion
Enforces fresh verification evidence before any completion claim. Use when about to claim "tests pass", "bug fixed", "done", "ready to merge", handing off work, or before editing when a request has ambiguous scope.
debugging
Systematic root-cause debugging: reproduce, investigate, hypothesize, fix with verification. Use when asked to "debug this", "fix this bug", "why is this failing", "troubleshoot", or mentions errors, stack traces, broken tests, flaky tests, regressions, or unexpected behavior.
ia-c-systems
C patterns for systems code, libraries, and native extensions: module layout, function decomposition, status-enum errors, memory safety, undefined behavior, and performance measurement. Use when writing, reviewing, refactoring, or debugging C, working with malloc lifetimes, buffer overflows, sanitizers, or Valgrind…
audit-and-fix
Audit an existing codebase, then autonomously implement the fixes it judges worth making against your next goal — composing deep-dive → triage → prompt-pack → build-loop to turn "here's what's wrong" into verified, receipted local commits + an honest ledger. ALWAYS invoke when the user says any of "audit this repo and…