performance-review

performance-review is a skill for Claude Code from zuoyebang/aiweave. It costs 98 tokens per session (3,426 once invoked), scanned A, original, Apache-2.0.

A code audit that checks changed Go code against documented performance rules, especially code used frequently or on request paths.

In plain words
What is it for?
Use it to review a branch diff, selected Go files, or only the project's documented hot paths, with findings linked to performance rule identifiers.
Why use it?
It helps find possible violations of memory, data-access, caching, back-pressure, runtime, and latency constraints before a human reviewer makes the final decision.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to review a branch diff, selected Go files, or only the project's documented hot paths, with findings linked to performance rule identifiers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zuoyebang/aiweave/performance-review
Install

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.

Any agent
npx skills add zuoyebang/aiweave --skill performance-review
Clone the repo
git clone --depth 1 https://github.com/zuoyebang/aiweave

Made for: Claude Code.

Wrote 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.

agentmods badge for performance-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/zuoyebang/aiweave/performance-review.svg)](https://agentmods.dev/skills/zuoyebang/aiweave/performance-review)
Your own site
<a href="https://agentmods.dev/skills/zuoyebang/aiweave/performance-review"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/performance-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,426 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.03426
Opus 5 $0.00049 $0.01713
Sonnet 5 $0.00020 $0.00685
Haiku 4.5 $0.00010 $0.00343

Measured 7d ago against content hash 99d402ea1ff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

performance-review 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 7d 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.

templates/skills/performance-review/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

审计代码的性能合约。范围:$ARGUMENTS(空则审计 git diff main..HEAD)。

公共步骤模板见 skills-spec/01_skill_authoring_guide.md §A-§E。本 Skill 不生成代码,故第 5 步测试同步不适用。

本 Skill 是 新增的审计类 Skill。"代码 ↔ 约束"一致性审计。

第 0 步:🚫 模块 + 启用状态检查

  1. BUILD_STATUS.md §0 —— 命中 🚫 模块的文件跳过审计
  2. INDEX.md §0 AIWeave 采纳进度 —— 如 docs-spec/22_performance_contract 标 ⬜ 未启用 → 跳过本 Skill,提示"本工程未启用 22,跳过 performance-review"

第 1 步:读取约束源

读以下文件(按顺序):

  1. docs/architecture/performance_contract.md —— §1 SLA + §2 热路径清单 + §3 内存预算 + §4 数据访问约束 + §6 背压策略 + §7 性能回归
  2. docs/architecture/ai_dev_guide.md §10.2 —— grep 锚 rule-id 索引(R-PERF-* / R-CACHE-* / R-LOCALMIRROR-STALE-READY);§10.10 尾延迟 / 运行时调优类(R-TAIL-*);§10.9 部署运行时(R-DEPLOY-GOMAXPROCS / R-RUNTIME-MEMLIMIT)
  3. docs/circuit_breaker/circuit_breaker_design.md §2 —— 熔断参数(避免与 22 双源真相)
  4. docs/BUILD_STATUS.md §11 —— 约束清单状态轨道

第 2 步:扫描代码范围

$ARGUMENTS 确定扫描范围:

  • 空 / 当前 PR:git diff main..HEAD --name-only 取新增/修改的 .go 文件
  • hot-path-only:仅取 performance_contract.md §2 清单中列出的文件
  • 文件路径:直接以该路径为范围

第 3 步:热路径分类

对每个被扫描的 .go 文件,判定其是否属于"热路径":

  • 在 §2 热路径清单中显式列出 → 热路径
  • 入口路由匹配 §2 清单中的路径 → 热路径
  • service 方法被热路径直接或间接调用(≤ 1 跳)→ 准热路径
  • 其他 → 普通路径

热路径文件适用 §3 全部 grep 锚 + §2.2 "禁止操作"列;普通路径仅适用 §3 中标 "all-paths" 的 grep 锚。

第 4 步:grep 锚检查(R-PERF-* 7 项 + R-DEPLOY/R-RUNTIME/R-TAIL 尾延迟 6 项 + SLO/profiling 2 项)

grep 锚定位为"信号级"非"判定级"。所有命中标 🟡 待复核;最终判定由人工 reviewer 决定。

R-DEPLOY-GOMAXPROCS / R-RUNTIME-MEMLIMIT / R-TAIL-* 多为信号级(🟡),grep 仅给线索,判定结合 deployment.md §4/§7 + performance_contract.md §6.4 时序与幂等语义。

检查 R-PERF-HOT-REFLECT:热路径用反射

范围:热路径 + 准热路径文件
grep 模式:'reflect\.'
误报排除:
  - 文件含 //go:build !hotpath 标记
  - 行末含 // aiweave:allow=R-PERF-HOT-REFLECT 注解

检查 R-PERF-HOT-FMT:热路径用 fmt.Sprintf

范围:热路径 + 准热路径文件
grep 模式:'fmt\.Sprintf\(|fmt\.Errorf\('
误报排除:
  - 错误路径(与 if err != nil 相邻)—— 错误路径不算热
  - 仅 fmt.Errorf 用于 wrap error
  - 行末含 // aiweave:allow=R-PERF-HOT-FMT 注解

检查 R-PERF-LOOP-DB-QUERY:for 循环内 DB 查询(N+1)

范围:所有路径
grep 模式:'for [^{]*\{[\s\S]{0,300}?\.(Find|First|Where|Take)\('
误报排除:
  - 显式批量 API(In(...) / Pluck / Scan)
  - 循环次数硬编码 ≤ {Loop-DB-safe}(如 < 5)
  - 行末含 // aiweave:allow=R-PERF-LOOP-DB-QUERY 注解

Read the full file on GitHub · 262 lines

Changes

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.

  1. 7d ago First seen · 262 lines · 98 tokens per session scan A 99d402ea1ff3

Subscribe to this mod's changes

performance-review is a skill published in the GitHub repository zuoyebang/aiweave (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 98 tokens to every session and 3,426 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

code-reviewer

Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.

MageByte-Zero/spec-superflow · 35 tokens

antidote

Stop AI agents from patching symptoms. Use this skill when coding, reviewing, refactoring, auditing, committing fixes, or adding guards, validation, workarounds, or 20+ lines without deleting code.

Avtr99/antidote · 47 tokens

repo-consistency-sweep

Proactive defect-class detection that handles the lower-value half of code review (per Bacchelli and Bird 2013) so human reviewers stay focused on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability…

Mozurok/fhorja.dev · 200 tokens

pr-feedback-ingest

Turn PR feedback (Greptile, CI, bots, humans) into a structured traceable backlog aligned with TASKSTATE.md, DECISIONS.md, and IMPLEMENTATIONPLAN.md so the next execution step can be a narrow implement-approved-slice or a small planning touch without losing alignment. Corrective scope only. Use when a PR is open or…

Mozurok/fhorja.dev · 230 tokens

review-hard

Review the current task changes for real correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Surfaces meaningful issues (not cosmetic feedback); not a replacement for external review systems. Returns no-op when the review would not materially…

Mozurok/fhorja.dev · 176 tokens

verify-against-rubric-fleet

Orchestrator-workers generalization of verify-against-rubric to N=many artifacts against ONE locked rubric. Dispatches N stateless Sonnet sub-agents in parallel; each receives ONE artifact + the SAME rubric + read-only tools (no TASKSTATE, no DECISIONS, no prior history); returns structured per-criterion verdict.…

Mozurok/fhorja.dev · 187 tokens