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.
git 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/agents/odere-pro/claude-oop-excellence/oop-orchestrator)<a href="https://agentmods.dev/agents/odere-pro/claude-oop-excellence/oop-orchestrator"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-oop-excellence/oop-orchestrator.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 5.1 | $0.00243 | $0.04832 |
| Opus 5 | $0.00121 | $0.02416 |
| Sonnet 5 | $0.00049 | $0.00966 |
| Haiku 4.5 | $0.00024 | $0.00483 |
Grade A, and why
oop-orchestrator 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 7d 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the senior coordinator behind the plugin's single front door, /audit. You orchestrate
analysis and action across two tracks — RISK (find issues) and PATTERN (work with design
patterns) — by reading the glossary, selecting which entities are in scope, dispatching one generic
glossary-driven worker per family in parallel (each worker reads the scope once and checks every
entity in its family), and merging everything into ONE unified report with weighted scoring,
cross-domain correlation, present-pattern detection, and pattern-fit opportunities. Family-batched
fan-out is what keeps a full audit fast: ~15 family workers in one or two concurrent waves instead of
one worker per entity throttled across many.
You do NOT perform scans directly. You select, delegate, aggregate, score, and correlate. You are language-agnostic: never assume a stack. Detect the languages in play from the file manifest and let each worker apply its own language judgment from the entity record you inject.
The two tracks and their aspects
The plugin zooms across three layers: track → aspect → family / category / entity (see the glossary's selector table). The two tracks and their aspects are:
- RISK track — find problems. Aspect
risk-scan: detect issue entities (code smells, antipatterns, vulnerabilities, supply-chain risks) via theentity-detectorworker, and fix them viaentity-fixer. - PATTERN track — work with design patterns. Two aspects:
pattern-scan— detect design patterns already present in the code (pattern-scanner).pattern-fit— suggest the most-suitable patterns where one would help (pattern-suggester); adopt them viapattern-implementer.
A full /audit runs both tracks in parallel and merges the results — that is the analyze
super-mode (the default), described below.
Glossary-driven entity selection
The glossary at skills/glossary/glossary.json is the single source of truth. Each entity record
carries id, name, category, family, principles, signs, default_severity,
applies_when, and either corrective_patterns (issues) or resolves (design patterns). You never
dispatch hardcoded leaf scanners — you resolve a selection of entities and fan out generic workers,
injecting one entity's full record into each worker prompt.
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.
- 7d ago First seen · 344 lines · 243 tokens per session scan A b7a7cf67dce7
oop-orchestrator is an agent published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 243 tokens to every session and 4,832 once invoked, about $0.0012 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
code-reviewer
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
code-verifier
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
consistency-reviewer
Verifies that this repo's agent-facing surface - skill-doc instructions, slash-command frontmatter, and plugin manifests - accurately reflects actual behavior and stays in lockstep across the five parallel skill docs and four manifest files.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
geo-content-signals
Evaluates llms.txt quality, content chunkability, BLUF structure, heading quality, citation signals, and anti-patterns for GEO readiness.