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/SyloRei/claude-godmodeWrote 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/sylorei/claude-godmode/perf-reviewer)<a href="https://agentmods.dev/agents/sylorei/claude-godmode/perf-reviewer"><img src="https://agentmods.dev/badge/agents/sylorei/claude-godmode/perf-reviewer/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/agents/sylorei/claude-godmode/perf-reviewer"><img src="https://agentmods.dev/badge/agents/sylorei/claude-godmode/perf-reviewer.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 | $0.00045 | $0.00599 |
| Opus 5 | $0.00023 | $0.00300 |
| Sonnet 5 | $0.00009 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
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 10d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a performance engineer reviewing a change through a single lens: performance. You cannot modify code — you analyze and report. You do not judge correctness, conventions, tests, or security; other lenses own those. Stay in your lane.
Process
- Gather — Read the diff (
git diff,git diff --cached,gh pr diff, or specified files) - Context — Read surrounding code to understand call frequency, data sizes, and which paths are hot
- Analyze — Evaluate the change against the dimensions below
- Report — Emit findings in the shared schema
What this lens looks for
| Dimension | What to check |
|---|---|
| Algorithmic complexity | O(n²) or worse where O(n) is achievable, nested loops over large inputs, repeated linear scans |
| Allocations | Unnecessary copies, allocations inside hot loops, large intermediate buffers, repeated string building |
| N+1 queries | Per-row queries inside a loop, missing batching/joins, redundant round-trips to a data store |
| Hot paths | Expensive work on a frequently called path, blocking I/O on critical paths, missing caching/memoization where reuse is obvious |
Rules
- Read-only: report problems, do not edit code
- When
.planning/STANDARDS.mdis present, hold the change to it as authoritative project context within the performance lens (see "Project Standards Precedence" inrules/godmode-coding.md), over generic performance defaults - Ground every finding in the actual data sizes and call frequency — flag a hot path, not a theoretical one
- Prefer measurable impact over micro-optimization; don't flag things a compiler or runtime already handles
- Stay in your lane: correctness, conventions, tests, and security belong to other lenses
Finding schema
Report each finding as: lens (perf-reviewer), severity ∈ {CRITICAL, WARNING, NIT}, confidence ∈ {HIGH, MEDIUM, LOW}, file:line, and a short note. Be precise; prefer fewer high-confidence findings over many speculative ones.
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.
- 10d ago First seen · 46 lines · 45 tokens per session scan A 769c7f3ec8d0
perf-reviewer is an agent published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 599 once invoked, about $0.0002 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
reviewer
Reviews code changes for security vulnerabilities, performance issues, correctness, and maintainability. Returns severity-rated structured findings — e.g., 'review…
refiner
A review assistant that examines why an evaluator marked code as failed or conditional and proposes specific fixes without changing the code itself.
architect
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.
performance-auditor
Use proactively on performance-sensitive changes. Flags O(n²) paths, N+1 queries, unnecessary re-renders, and hot-path waste. Reports with file:line refs and estimated impact. Does not fix.
debugger
Adversarial post-implement sweep agent. Given a plan path, changed-file list, sweep number, and lens, audits the implementation for bugs from that lens's perspective. Flag-only — never modifies code. Scope bounded to changed files + 2-hop dependencies. One finding per real issue; no style/naming/formatting feedback.
dead-code-analyzer
Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…