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 hereinthehive/gotrino-assistant --skill design-debtgit clone --depth 1 https://github.com/hereinthehive/gotrino-assistantWrote 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/hereinthehive/gotrino-assistant/design-debt)<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/design-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/design-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/hereinthehive/gotrino-assistant/design-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/design-debt.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.00674 |
| Opus 5 | $0.00023 | $0.00337 |
| Sonnet 5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
design-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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Debt
Surface drift — the gap between how the codebase was meant to be structured and how it actually is.
Philosophy
"Is our system getting harder to reason about because of drift?"
Design debt is quiet. No test fails, no lint warns. But new contributors ask more questions, changes take longer, bugs appear in "how do these modules talk to each other." Design-debt finds the drift before it compounds.
Not a refactoring plan. The value is spotting inconsistency, not prescribing a fix. The team decides whether to realign or to formalize the new pattern.
Scope
User may specify a directory. Default: ask which part of the codebase to focus on. This skill works best on a bounded slice (a module, a layer), not whole-codebase scans.
Config Integration
Follow references/config-migration.md for preflight.
Read .assistant-config.md for:
- Architecture Principles (optional — ground truth if declared)
- Stack
- Acknowledged Debt
If no architecture principles are declared, infer the dominant pattern from the code and flag deviations.
Stack Detection
Language/framework context matters (Express vs. Next.js handlers have different norms). Detect via manifest as in other dimensions.
Process
1. Understand context
Read a representative handful of files in the scope. Identify:
- The dominant structural pattern (e.g. "handlers are thin, delegate to services")
- The dominant error-handling style (e.g. "try/catch, JSON envelope")
- The dominant naming convention
2. Scan
- Error handling inconsistency: read all handlers (or equivalent). Compare error shapes.
- Response shape inconsistency: same, for success responses.
- Naming inconsistency: Glob filenames, Grep function names.
- Architectural drift: Grep for imports that cross declared boundaries (e.g. services importing handlers, handlers doing direct DB calls).
- Duplicated logic: Grep for similar function signatures across files.
3. Group by concern
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.
- 12d ago First seen · 79 lines · 45 tokens per session scan A 21dcb116bb7a
design-debt is a skill published in the GitHub repository hereinthehive/gotrino-assistant (5 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 674 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…