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 skills/movebrickschi/harness-engineering-mcp/perf-flownpx skills add movebrickschi/harness-engineering-mcp --skill perf-flowgit clone --depth 1 https://github.com/movebrickschi/harness-engineering-mcpWrote 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/skills/movebrickschi/harness-engineering-mcp/perf-flow)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/perf-flow"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/perf-flow.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 | $0.00080 | $0.01069 |
| Opus 5 | $0.00040 | $0.00535 |
| Sonnet 5 | $0.00016 | $0.00214 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
perf-flow 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.
What it actually says
perf-flow
适用场景
页面慢、接口慢、内存高、CPU 高、bundle 大等性能问题。
前置条件
确认 _playbook.md Part B.3 启动参数；额外 perf_target（待优化的页面/接口/作业）+ perf_metric（耗时？吞吐？内存？）+ perf_goal（目标值）。
流程步骤
阶段 0 · 上下文初始化
move_agent_to_root；建知识库目录（极简 META.md）。
阶段 1 · 基线 benchmark
- 用
/benchmark（前端 web vitals）或cursor-ide-browser的browser_profile_start/stop（性能录制）建立基线 - 后端：用现有 APM、日志、
ab/wrk/k6跑基准 - 输出
PERF_BASELINE.md：当前数值 + 测试条件 + 数据样本
阶段 2 · Profile 找瓶颈
- 前端：Chrome Performance、
browser_profile_*、/benchmark的 web vitals 拆解 - 后端：APM 火焰图、慢日志、DB explain
- 输出
BOTTLENECK.md：top 3 热点 + 数据证据
阶段 3 · 优化方案 + 卡点
prompt: "瓶颈定位完成（BOTTLENECK.md）。优化方案："
options:
- "方案 A（首选）"
- "方案 B（更激进）"
- "需要更多 profile"
阶段 4 · 单一变量优化
- 每次只改一处，commit
perf(scope): 优化 [瓶颈点] - 改完立刻 micro-benchmark 对比，写入
PERF_DIFF_[step].md
阶段 5 · 全量 re-benchmark
- 用阶段 1 同条件再跑一遍
/benchmark - 输出
PERF_FINAL.md：基线 vs 终态对比 - 未达
perf_goal→ 回阶段 2 再 profile
阶段 6 · 自查
/qa（确保功能未退化）+ /review。
阶段 7 · 上线
/ship → /land-and-deploy → /canary（重点监控同指标）。
阶段 8 · 复盘
append _lessons.md：瓶颈类型 + 优化手法 + 收益数据。
错误处理
- 优化后功能 broken → 立即 revert，回阶段 2 找新瓶颈
- benchmark 数据波动太大 → 增加样本数 / 固定测试环境
- 达不到 goal 但已无明显瓶颈 → 与用户讨论调整 goal 或更换方案
产物清单
META.md、PERF_BASELINE.md、BOTTLENECK.md、若干 PERF_DIFF_*.md、PERF_FINAL.md、PR 链接。
支持的修饰符
无标准修饰符；可叠加 M4（如优化包含建索引/分表）→ 必出 MIGRATION_PLAN.md。
与其他 skill 的关系
- 通常被
/dev-flow路由到（也可被用户直接触发） - 强依赖
/benchmark与cursor-ide-browserprofile 工具 - 自查：
/qa、/review - 上线：
/ship、/land-and-deploy、/canary
附录
- 通用基座：见 _playbook.md Part B
- 文档模板：见 _playbook.md Part E
- 完整索引：见 _playbook.md Part F
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 · 103 lines · 80 tokens per session scan A 5a3a5aec375a
perf-flow is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 1,069 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…