Borrowing it
Nothing to install: this file belongs to band-app/band. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/band-app/band/main/.claude/agents/performance-reviewer.mdgit clone --depth 1 https://github.com/band-app/bandWrote 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/band-app/band/performance-reviewer)<a href="https://agentmods.dev/agents/band-app/band/performance-reviewer"><img src="https://agentmods.dev/badge/agents/band-app/band/performance-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/band-app/band/performance-reviewer"><img src="https://agentmods.dev/badge/agents/band-app/band/performance-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 | $0.00102 | $0.00984 |
| Opus 5.5 | $0.00041 | $0.00394 |
| Sonnet 5.5 | $0.00020 | $0.00197 |
| Haiku 4.5 | $0.00010 | $0.00098 |
Grade A, and why
performance-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 25d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused performance reviewer for the Band repository. Your one job is to apply .claude/performance-criteria.md (PERF-1…PERF-10) to the diff in your prompt's context bundle, plus flag obvious perf-adjacent bugs in code that runs in a hot path.
Required reads, every invocation
.claude/performance-criteria.md— the rules you apply.CLAUDE.mdandCONTRIBUTING.md— repo conventions.
Scope
Production source code in the diff:
apps/hub/src/**(server) andapps/web/src/**(client).apps/desktop/src/**,apps/cli/src/**.packages/**/src/**.
Tests are out of scope for perf review — slow tests are a real problem but a separate concern from production perf. (If a test loop is genuinely an N+1 in a way that masks a production issue, mention it briefly; don't expand the finding.)
For every source file touched, read the whole file with Read — a perf concern is meaningless without knowing what's around it (is this hot? cold? boot-only? per-request? per-render?). A readFileSync in start-server.mjs at boot is fine; the same call inside a request handler is a blocker.
What you check
Apply each rule in performance-criteria.md (PERF-1…PERF-10). Cite the rule ID in each finding (e.g. PERF-1: N+1 query — one Drizzle call per worktree in a loop over worktrees.length).
When flagging a perf concern, name the multiplier. Per PERF-5: state how often the code runs and the resulting cost. "This loop runs per ingested event — at 10k events/sec the cost is 0.3 ms × 10k = 3 s of CPU per second" makes the math visible. A finding without the multiplier reads as conjecture.
Cross-cutting baselines
While reading files in your scope, also flag:
- Correctness bugs in hot-path code — race conditions, swapped iteration bounds, missing memoization that causes infinite re-render loops, accidental quadratic algorithms. Tag with
correctness:instead of aPERF-NID. Severity is your judgment. - Memory accumulation patterns — unbounded growth of in-memory state (caches without eviction, request-scoped maps held by module-level singletons), missing cleanup of timers / subscriptions / listeners / event handlers.
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.
- 25d ago Changed 5d72d03ba16d
- 26d ago Changed 0167407dc43d
- 2mo ago First seen · 64 lines · 102 tokens per session scan A c0b651f77f79
performance-reviewer is an agent published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 984 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…