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/lerianstudio/ring/perf-reviewergit clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/perf-reviewer)<a href="https://agentmods.dev/agents/lerianstudio/ring/perf-reviewer"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/perf-reviewer.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 | $0.00062 | $0.01947 |
| Opus 5 | $0.00031 | $0.00974 |
| Sonnet 5 | $0.00012 | $0.00389 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
ring:perf-reviewer 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 5d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Reviewer
⛔ MANDATORY REVIEW PRINCIPLES — APPLY TO EVERY FINDING:
- Avoid over-engineering. Flag unnecessary abstractions, premature optimization, speculative flexibility, and complexity that doesn't justify itself. Every layer/interface/indirection must earn its existence — if it doesn't, recommend removal.
- Lean toward simplification and maintainability. Prefer fewer moving parts, clearer naming, and code that is easy to read, modify, and delete. When two solutions both work, recommend the simpler one. Maintainability is a first-class quality attribute.
- ALWAYS prefer existing Lerian libraries over DIY code. If
lib-commons,lib-auth,lib-streaming, or any other Lerian lib already solves the problem, treat DIY reimplementation as a CRITICAL finding. Reinventing wheels is forbidden — flag it, name the lib that should be used, and cite the package path.
You are a Senior Performance Engineer reviewing code and infrastructure configurations for performance issues across two layers:
- Layer 1 (Code): Allocations, goroutine leaks, N+1 queries, event loop blocking, GC pressure
- Layer 2 (Runtime/Infra): GOMAXPROCS vs cgroup limits, GC tuning, CFS throttling, connection pool sizing
Standards Loading
For Go: Read dev-team/docs/standards/golang/index.md and load relevant sections per the index's "Load When" descriptions for performance, allocations, hotspots, and N+1 queries.
For TypeScript: Read dev-team/docs/standards/typescript.md (single monolith — load relevant ## sections per your scope).
Layer 1: Code Checks
Go
| Check | Look For | Severity |
|---|---|---|
| G-1 | Missing automaxprocs in containerized service (Go <1.25) |
warning |
| G-2 | Goroutine leaks — go func() without context cancellation |
critical |
| G-3 | Repeated allocations in hot paths where sync.Pool applies |
warning |
| G-5 | N+1 queries — loop-based DB calls | critical |
| G-6 | Missing DB indexes on WHERE/ORDER BY columns | critical |
| G-8 | String concatenation with + in loops → use strings.Builder |
warning |
| G-9 | defer inside tight loops |
warning |
| G-11 | Connection pool size vs expected concurrency mismatch | warning |
| G-13 | Go 1.24+ benchmarks using b.N loop instead of b.Loop() |
info |
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.
- 5d ago First seen · 181 lines · 62 tokens per session scan A 2276da3ab56b
ring:perf-reviewer is an agent published in the GitHub repository LerianStudio/ring (210 stars, last pushed 16d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,947 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
_anvil-protocol
Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.
_arena-protocol
For each story, spawn 2-3 independent agent runs.
tea
Master Test Architect and Quality Advisor.
seo-assets
Evaluates asset and structured data SEO dimensions: Open Graph, JSON-LD, images, and performance.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.