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 dep-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/dep-debt)<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/dep-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/dep-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/dep-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/dep-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 | $0.00624 |
| Opus 5 | $0.00023 | $0.00312 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
dep-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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dep Debt
Surface dependency debt and point at the packages most likely to bite.
Philosophy
"Which dependencies will bite us, and when?"
Every dependency is a bet: that it'll keep working, stay maintained, not have vulnerabilities. Old bets decay. Some libs went abandoned years ago; some pinned versions missed a major release; some packages are installed and imported nowhere. Dep-debt is the audit of those bets.
Not a replacement for npm audit / pip-audit. This skill reads manifests statically and spots patterns. For vulnerability scans, use the ecosystem tool — this skill tells you where to look.
Scope
User may specify a directory. Default: project root. For monorepos, scan all manifests found.
Config Integration
Follow references/config-migration.md for preflight.
Read .assistant-config.md for:
- Stack (which manifests are expected)
- Acknowledged Debt (deps acknowledged as pinned-intentionally)
Stack Detection
Glob for all supported manifests (see references/dep-debt-manifests.md). In a monorepo, expect multiple.
Process
1. Understand context
List all manifests found. Read each. Note declared deps, versions, lockfile presence.
2. Scan
- Outdated / pre-1.0 versions: compare declared versions to signals in the reference.
- Abandoned packages: match against the known-deprecated list.
- Unused deps: for each declared dep, Grep the source for
import/require/from X import. If no match, flag as "appears unused; verify build scripts". - Version drift: in monorepos, compare the same dep across manifests.
3. Group by manifest
Organize findings per manifest file. A monorepo with three packages should produce three location groups, not one flat list.
4. Assess impact
- High: abandoned packages on runtime critical paths, deps with known major security incidents
- Medium: pre-1.0 versions of stable libs, version drift
- Low: dev deps slightly behind, small unused deps
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 · 72 lines · 45 tokens per session scan A 30e9a447dc3a
dep-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 624 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…