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/commands/odere-pro/claude-oop-excellence/fix-risks)<a href="https://agentmods.dev/commands/odere-pro/claude-oop-excellence/fix-risks"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-oop-excellence/fix-risks/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/commands/odere-pro/claude-oop-excellence/fix-risks"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-oop-excellence/fix-risks.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 | $0.00090 | $0.01391 |
| Opus 5.5 | $0.00036 | $0.00556 |
| Sonnet 5.5 | $0.00018 | $0.00278 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
fix-risks 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 1mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The gated FIX action front door — the side-effecting command that the /audit report's
Recommended Actions section hands off to. Run the fix verb against this repository. Because it
writes to your source tree, it is user-invoked only. It resolves your selection against the
glossary (skills/glossary/glossary.json) and delegates to the improve skill, which drives the
oop-orchestrator in fix mode (one entity-fixer per in-scope entity, fanned out in parallel
batched by family). Each fixer detects instances of its one injected entity, applies the smallest
corrective refactor, and verifies with the project's own detected test/typecheck/lint commands.
Selection grammar
[<entity-id> | <family> | all] [full | changed | component <path>] [--plan-only]
- Selection (default
all) — a single glossary issue id (e.g.god-class,feature-envy,shotgun-surgery), an issue family (oop,code,architecture,testing,concurrency,database,security,dependency), orallissue entities. - Scope (default
full) —full,changed(vs the base branch), orcomponent <path>. --plan-only(or a leadingplantoken) — produce the corrective plan (detected instances + intended diffs) and make no edits. Use it to preview the refactor before committing to it.
Only issue entities are in scope for the fix verb — design patterns belong to /implement-patterns.
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). -
Check for the most recent saved
/auditreport for context (optional, not required):ls -t tmp/audit-report-*.md 2>/dev/null | head -1If one exists, read it to prioritise which entities have live findings — its Recommended Actions section is the handoff that points here. If none exists, proceed — the fix verb re-detects within scope; you do not need a report to run.
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.
- 1mo ago First seen · 117 lines · 90 tokens per session scan A c5653eb53263
fix-risks is a command published in the GitHub repository odere-pro/claude-oop-excellence (0 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 1,391 once invoked, about $0.0004 per session on Opus 5.5. 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
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
lint
The canonical linter per ecosystem over your changes: findings are diagnoses you judge, fix, or explain.
verify
A command that independently checks the factual claims and file-and-line references in an agent’s most recent response. It reports whether each claim is confirmed, outdated, missing, or unsupported.
doctor
Check OCR installation and verify all dependencies are available.
sm-refit
Run slop-mop's one-time onboarding remediation rail for this repository.
logic-fix-all
Autonomous audit-and-fix — after consent, scan the target, fix every logic issue found (all severities), verify each fix, and report anything unresolved.