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 skills/odere-pro/claude-oop-excellence/pattern-implementnpx skills add odere-pro/claude-oop-excellence --skill pattern-implementgit 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/pattern-implement)<a href="https://agentmods.dev/skills/odere-pro/claude-oop-excellence/pattern-implement"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/pattern-implement.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.02337 |
| Opus 5 | $0.00049 | $0.01169 |
| Sonnet 5 | $0.00020 | $0.00467 |
| Haiku 4.5 | $0.00010 | $0.00234 |
Grade A, and why
pattern-implement 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 3d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Implementer
The IMPLEMENT action — the Layer 1 action of the PATTERN track. Locate → scaffold alongside →
migrate call sites → remove the old path + verify, one glossary design pattern at a time, in any
language. This is the action layer reached from the /audit report's Recommended Actions
handoff: audit recommends /implement-patterns <selection> for a high-confidence pattern
opportunity, and that command drives this implement flow. This skill resolves the requested pattern
against the glossary, then delegates the work to the oop-orchestrator in pattern-implement
mode, which fans out one pattern-implementer worker per in-scope pattern. It assumes nothing about
the language or stack.
Because this skill writes to your source tree, it is user-invoked only
(disable-model-invocation: true) and never auto-fires.
Selection grammar
[plan] <pattern-id> [full | changed | component <path>] [--plan-only]
The recommended, primary use is one pattern at a time — name a single <pattern-id>. A leading
plan verb or a trailing --plan-only flag plans without writing any files. Batch selection by
family or all is also accepted, but prefer a single, deliberate pattern per run.
Pattern selection (no default — name a pattern)
The unit of work is a glossary design-pattern entity, not a hardcoded catalog. Resolve the
selection against skills/glossary/glossary.json:
<pattern-id>(primary) — a single design pattern (e.g.strategy,facade,chain-of-responsibility,repository).<family>— every design pattern in one pattern family (creational,structural,behavioral,architectural,enterprise,functional,ddd). Use sparingly — batch implementation changes many call sites at once.all— every design-pattern entity. Reserve for surveys; a single pattern is the safer unit.
Only design-pattern entities are in scope for the implement verb — issues (code smells,
antipatterns, vulnerabilities, supply-chain risks) are the province of /improve.
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.
- 3d ago First seen · 173 lines · 98 tokens per session scan A 74dcf3b92c9a
pattern-implement is a skill published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 2,337 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
smell-check
Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code smells and test smells with evidence strength. Use for smell audit, code smell scan, whole-repo audit, tech debt scan, test smell check, maintainability audit, or duplication and nesting…
avvarre
Analyze code quality against Google style guides for 21 languages/formats. Fix-verify loops, compressed task sync, workspace heatmaps.
release-cut
Cut and verify a CADENCE release end-to-end — inventory unreleased phases, audit changesets, lockstep version bump, a full doc-sync verification pass (automated doc tests + manual stale-version-reference sweep), release PR, operator-triggered Release workflow, and independent npm/tag/GitHub verification. Use when the…
pr-land
Land a branch through cadence's protected-main pipeline — local preflight, commit hygiene, push, PR, ci-success babysitting with the known-flake protocol, consent-gated squash merge, and post-merge sync. Use when work is ready to land, the user says "land this", "open a PR", "merge when green", or a PR is sitting on…
avvarre:autopilot
Autonomous fix-verify loop that keeps fixing violations until the file reaches Grade A (90+).
avvarre:garden
Audit .avvarre/ project memory for context drift, stale tasks, and conventions mismatches.