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 agentmods add commands/odere-pro/claude-oop-excellence/implement-patternsgit clone --depth 1 https://github.com/odere-pro/claude-oop-excellenceWhat 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 | $0.00094 | $0.01746 |
| Opus 5 | $0.00047 | $0.00873 |
| Sonnet 5 | $0.00019 | $0.00349 |
| Haiku 4.5 | $0.00009 | $0.00175 |
Grade A, and why
implement-patterns 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 yesterday.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the implement verb against this repository. This is the gated IMPLEMENT action front door —
the command the /audit report's Recommended Actions section hands off to for a high-confidence
pattern opportunity (/implement-patterns <selection> <scope>). It writes to your source tree, so
it is user-invoked only. It resolves your selection against the glossary
(skills/glossary/glossary.json) and delegates to the pattern-implement skill, which drives the
oop-orchestrator in pattern-implement mode (one pattern-implementer per in-scope design
pattern). Each implementer applies its one injected pattern through the safe 4-step refactoring
sequence, running the project's own detected tests at every checkpoint.
Selection grammar
[<pattern-id> | <category> | all] [full | changed | component <path>] [--plan-only]
- Selection (default
all) — a single design-pattern id (e.g.strategy,facade,repository), a pattern category (creational,structural,behavioral,architectural,concurrency,enterprise,functional,ddd), oralldesign patterns. - Scope (default
full) —full,changed(vs the base branch), orcomponent <path>. --plan-only(or a leadingplantoken) — produce the implementation plan and make no edits. Use it to preview the change set before committing to it.
Only design-pattern entities are in scope for this verb — issue entities belong to /fix-risks.
Phase 1 — Parse and acquire context
-
Parse
$ARGUMENTSinto a selection (defaultall), a scope (defaultfull), and the optional--plan-onlyflag (set it when--plan-onlyor a leadingplantoken is present). -
If this run was handed off from an
/auditreport's Recommended Actions (the selection and scope came straight from a namedPattern Opportunitiesrow), use that opportunity's fit confidence to prioritise which patterns have the strongest signal. If you arrived here directly, proceed — the implement verb evaluates fit within scope. For a fresh read of which patterns would help, run/audit pattern-fit <scope>first.
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.
- yesterday First seen · 143 lines · 94 tokens per session scan A 517a45c40d04
implement-patterns is a command published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,746 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 commands, from other repositories
avvarre:init
Analyse the current workspace, then scaffold .avvarre/ with real project context, conventions, and task tracking.
handoff
End-of-session handoff — reconcile memory + docs, write a SESSION handoff doc, commit & push so another LLM can resume cleanly.
avvarre:autopilot
Autonomous fix-verify loop that keeps fixing violations until the file reaches Grade A (90+).
avvarre:garden
Audit the workspace persistent memory folders (.avvarre/) to detect context drift, conventions mismatch, and stalled task lists.
avvarre
Analyze the currently active file for code quality violations against Google style guides.
avvarre:pr
Analyze only the files changed in the current git branch to enforce quality on new code.