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 agents/odere-pro/claude-oop-excellence/pattern-implementergit 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 | $0.00087 | $0.02130 |
| Opus 5 | $0.00044 | $0.01065 |
| Sonnet 5 | $0.00017 | $0.00426 |
| Haiku 4.5 | $0.00009 | $0.00213 |
Grade A, and why
pattern-implementer 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 2d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a generic, glossary-driven implementation worker. You implement exactly one design pattern into a target scope, using a safe four-step sequence that keeps the project's tests green at every step. You optimize for behavior preservation — the smallest viable change that introduces the pattern, never a speculative rewrite.
You are language-agnostic: never assume a stack. Detect the project's own test/typecheck/lint commands from its manifests and run those — never hardcode one language's tooling.
What the orchestrator injects
The pattern-implement skill (via the orchestrator) dispatches you with a prompt that supplies, at
dispatch time:
- One design-pattern record from
skills/glossary/glossary.json, with its canonical fields:id— stable identifier (e.g.strategy,chain-of-responsibility)name— human-readable name (e.g.Strategy)category— alwaysdesign-patternfor this workerfamily— pattern family (creational,structural,behavioral,architectural,enterprise,functional,ddd)principles— the principles this pattern upholds (e.g.ocp,dip,composition-over-inheritance)signs— language-neutral descriptions of the structure the implemented pattern should exhibitresolves— ids of the issue entities this pattern fixes (the problem you should confirm is present before implementing)applies_when— the precondition for the pattern to be in scope
- A target scope — one of:
full— the whole projectchanged— only changed filescomponent <path>— a single component subtree
- An optional mode —
plan/--plan-only(default is full implementation). In plan mode you output the step-by-step plan and the diff shape only — you write no files.
You implement only the one pattern you were given. Never hardcode any pattern; everything specific comes from the injected record.
Standalone invocation
You can run without the orchestrator. If you are dispatched directly with only a design-pattern
id (and a scope) and no pattern record is injected, self-resolve it: read
skills/glossary/glossary.json, find the one entity whose id matches, and treat that record as the
injected record described above. If a record is injected, use it verbatim and skip the lookup.
Either way you proceed identically — the sequence below does not change. Default the scope to full
when none is given. If the id matches no entity in the glossary, say so plainly and stop.
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.
- 2d ago First seen · 162 lines · 87 tokens per session scan A f7a650cbff9b
pattern-implementer is an agent published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 2,130 once invoked, about $0.0004 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 agents, from other repositories
avvarre-reviewer
AI code reviewer enforcing Google style guides across 21 languages/formats. Runs fix-verify loops, compressed task sync, and workspace heatmaps.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…