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 odere-pro/claude-oop-excellence --skill onboardinggit clone --depth 1 https://github.com/odere-pro/claude-oop-excellenceWrote 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/odere-pro/claude-oop-excellence/onboarding)<a href="https://agentmods.dev/skills/odere-pro/claude-oop-excellence/onboarding"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/onboarding/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/odere-pro/claude-oop-excellence/onboarding"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/onboarding.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 | $0.00109 | $0.01243 |
| Opus 5 | $0.00055 | $0.00622 |
| Sonnet 5 | $0.00022 | $0.00249 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
onboarding 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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Getting started with claude-oop-excellence
This plugin enforces good object-oriented design in any programming language: you audit a codebase, get one unified read-only report, then apply gated, test-verified fixes. It hunts God Classes, Anemic Domain Models, Feature Envy and the rest, then refactors toward sound design with proven patterns (Strategy, Facade, Decorator…) — no framework, stack, or paradigm lock-in.
This orientation changes nothing. It explains the mental model and the shortest path to value, then points you at the deeper docs. Run a real audit when you are ready.
The mental model
One front door, three layers, two tracks.
- One front door —
/auditis the single, read-only analysis entry point. With no selector it runs everything and merges it into ONE unified report. - Three layers —
/auditresolves a selector against the glossary and zooms across track → aspect → family / category / entity:- L1 — the full run (
/audit, both tracks together). - L2 — a single track or aspect.
- L3 — a single family, category, or entity id.
- L1 — the full run (
- Two tracks — every full audit runs both in parallel:
- RISK — antipatterns, code smells, vulnerabilities, supply-chain risks.
- PATTERN — two aspects: scan (design patterns already present) and fit (most-suitable pattern suggestions).
A full /audit is read-only end to end. The report closes with a Recommended Actions handoff
that prints the exact gated commands to run next — nothing is modified until you run one yourself.
The 60-second path
- Analyze (read-only). Run
/auditfor the whole project, or/audit changedfor just the files changed versus the base branch. - Read the unified report. You get risk findings (matrix, hotspots, correlations, an aggregate score), Patterns Present, Pattern Opportunities, and a Recommended Actions section.
- Act (gated, your call). Run the exact
/fix-risksor/implement-patternscommand the report prints, scoped to what it found. Add--plan-onlyto preview the change without writing.
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.
- 9d ago First seen · 94 lines · 109 tokens per session scan A 365884ff6b36
onboarding is a skill published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,243 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
code-review
Review code against enterprise standards — auto-detects stack (.NET, NestJS, React, RN, Flutter).
pr-review
Review current branch changes — reads git diff, runs stack-appropriate review, outputs structured feedback.
security-review
Review code for security vulnerabilities — SQL injection, XSS, hardcoded secrets, weak crypto, PII exposure.
architecture-review
Review layer separation, design patterns, DI, and module boundaries.
performance-review
Review for N+1 queries, missing memoization, unbounded queries, re-renders, caching gaps.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…