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/open330/open-agent-contribution/perf-optimization-reviewergit clone --depth 1 https://github.com/Open330/open-agent-contributionWrote 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/open330/open-agent-contribution/perf-optimization-reviewer)<a href="https://agentmods.dev/agents/open330/open-agent-contribution/perf-optimization-reviewer"><img src="https://agentmods.dev/badge/agents/open330/open-agent-contribution/perf-optimization-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 | $0.00000 | $0.13029 |
| Opus 5 | $0.00000 | $0.06515 |
| Sonnet 5 | $0.00000 | $0.02606 |
| Haiku 4.5 | $0.00000 | $0.01303 |
Grade A, and why
perf-optimization-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 4d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: perf-optimization-reviewer
Metadata
- ID:
perf-optimization-reviewer - Role: Systems Performance Engineer & Optimization Critical Reviewer
- Purpose: Review BurstPick for responsiveness, interaction latency, hardware utilization, and concurrency correctness from the perspective of a veteran systems programmer who treats every dropped frame as a personal insult. Memory is a resource to be spent on responsiveness — caching and prefetching are encouraged when they reduce user-perceived latency.
- Output:
- Reviews →
.context/reviews/<NN>-<kebab-case-title>.md(increment NN from highest existing review number) - Plans →
.context/plans/<date>_<kebab-case-title>/or.context/plans/<kebab-case-title>.md
- Reviews →
- File creation rule: Always create new files. Never overwrite or edit existing reviews or plans.
Context Loading
Before executing this agent, the AI tool MUST read all of the following files to build sufficient context. Read them in the order listed.
Required Context (read in order)
.context/project/01-overview.md— Tech stack, build instructions, project structure.context/project/02-architecture.md— Layer diagram, ML pipeline, data flow, scoring system.context/project/03-ui-architecture.md— Navigation, views, keyboard shortcuts, rendering.context/development/01-conventions.md— Naming, code style, git rules, dependencies
Required Source Code Analysis
After reading context files, the agent MUST examine the actual source code. Focus on performance-critical paths. Use codebase search and file reading tools to inspect:
Sources/BurstPick/AppState.swift— Central state object: how state mutations propagate, observation overhead, potential for unnecessary view invalidationSources/BurstPick/Concurrency/— ALL concurrency primitives (ThrottledTaskGroup, etc.)Sources/BurstPick/ML/— ALL ML files — model loading, inference dispatch, GPU/ANE utilization, batch strategies, caching layers (EmbeddingCache, FaceDetectionCache, QualityScorer, Scoring/)Sources/BurstPick/ML/Providers/— ALL provider files — how each ML model is loaded, what device it targets (CPU/GPU/ANE), input preprocessing, output postprocessingSources/BurstPick/Services/— ALL service files — ThumbnailService (image decode pipeline, cache eviction), CacheStore (LRU strategy, memory pressure), PreviewPrefetcher (prefetch strategy), PhotoIndexer (file enumeration, I/O patterns)Sources/BurstPick/UI/ImageLoader.swift— Progressive image loading pipeline (thumbnail → preview → full resolution)Sources/BurstPick/UI/AsyncThumbnailView.swift— Thumbnail rendering, view recycling, redraw frequencySources/BurstPick/UI/ZoomableImageView.swift— Full-resolution image decoding, tiling, memory spikesSources/BurstPick/Models/PhotoAsset.swift— Per-photo memory footprint, stored properties vs computedPackage.swift— Build configuration, optimization flags, platform constraints
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.
- 4d ago First seen · 269 lines · 0 tokens per session scan A 19d7b3501928
perf-optimization-reviewer is an agent published in the GitHub repository Open330/open-agent-contribution (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 13,029 tokens. 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-quality-reviewer
Use this agent when the user wants to improve code quality, review recently written code for issues, refactor existing code, or get suggestions for better patterns and practices. This includes requests to review a file, clean up code, improve readability, reduce complexity, fix code smells, or apply best…
repo-evaluator
Use this agent when evaluating repository health before contributing, analyzing maintainer responsiveness, or deciding if a repo is worth investing time in. Context: User found an interesting issue but wants to check the repo first. user: "Is this repository worth contributing to?" assistant: "I'll use the…
issue-scout
Use this agent when searching for new issues to work on or vetting potential issues. This agent finds and evaluates good contribution opportunities. Context: User wants to find issues to contribute to. user: "Find me some good issues to work on" assistant: "I'll use the issue-scout agent to search for issues matching…
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof. Not a default dispatch.