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/ccdawn/codex-skills/briefbound-performance-engineeringnpx skills add CCDawn/codex-skills --skill briefbound-performance-engineeringgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote 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/ccdawn/codex-skills/briefbound-performance-engineering)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-performance-engineering"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-performance-engineering.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 | $0.00086 | $0.01272 |
| Opus 5 | $0.00043 | $0.00636 |
| Sonnet 5 | $0.00017 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
briefbound-performance-engineering 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound 性能工程
目标
用最小测量找到真正限制结果的瓶颈，只保留收益超过噪声与复杂度成本的优化。普通开发不经过本 skill。
Briefbound task contract
- Context Boundary: 已确认的性能目标或强信号、代表性负载、owning surface、现有指标/benchmark/profile、正确性契约和允许写入范围。
- Output Contract: baseline、主要瓶颈、最小优化、同负载对比、取舍、正确性验证和必要的回归保护。
- Allowed Action: 读取相关代码和运行证据，执行有界 benchmark/profile，修改已授权 scope 并运行相关验证；不自动安装全局工具、不压测生产、不扩大产品行为。
- Success Evidence: 相同负载下有可比较的 before/after，收益超过测量噪声或目标已满足，且正确性验证通过。
- Stop Condition: 没有性能强信号、无法建立安全负载、瓶颈不在可改范围、需要高风险架构取舍、收益不足以抵偿复杂度，或目标已经满足。
- Route Out: 当前开发 owner、
briefbound-bug-review、briefbound-pr-review、briefbound-development-cleanup、briefbound-router或 BLOCKED。
统一调用契约
- 只处理 Briefbound task contract 范围；不匹配时回最具体 owner。用户可见内容默认中文，保留指标、命令、路径、API 和工具名。
- Route Out 仅以 Briefbound task contract 为准；末行写
下一步建议: <一个具体动作>。 - 不把性能工程变成固定开发阶段，也不要求用户逐步确认已授权的测量、优化和验证。
三档边界
Briefbound Router 使用 FAST / CHECK / PROFILE：
FAST：低频、低规模、机械修改，直接开发和验证，不输出性能检查。CHECK：当前 owner 静默处理已定位的 N+1、循环 I/O、重复全量计算、隐藏高阶复杂度和无界增长；批量修复及查询/调用次数断言仍是确定性验证，不加载本 skill、不建 benchmark，也不因“发现问题”切到 bug owner。只有存在已观察到的故障、正确性回归或待诊断根因时才路由briefbound-bug-review。PROFILE：明确性能目标/回归，或功能进入高频热路径、大数据量、并发、缓存、批处理、流式 I/O、持久化、包体/启动关键面时，才进入本 skill。
文件多、描述长、可能“以后会扩展”或一般性最佳实践不触发 PROFILE。PR/diff 审查仍由 briefbound-pr-review 主责，本 skill 只在需要性能测量证据时作为 support。
最小测量循环
- 锁定一个主指标和代表性负载：延迟分位、吞吐、CPU、内存、I/O、查询/请求次数、包体或启动时间。没有目标阈值时，以当前回归或稳定 baseline 为比较点。
- 优先复用现有 benchmark、trace、日志、query plan 或 profiler；选择能区分方案的最小 probe。确定性调用次数、查询数或复杂度证据足够时，不制造负载测试。
- 找一个主要限制点，区分算法/重复工作、数据库/网络、分配/序列化、锁/队列、缓存、下游依赖和环境噪声；不做全仓性能扫描。
- 实施一个最小修改。优先消除无效工作和改进算法/数据访问，再考虑批处理、缓存或并发；微优化最后。缓存、线程池和并行不能凭直觉加入。
- 在相同负载下复测并运行正确性检查。记录方差或至少重复结果；延迟敏感链路优先看 p95/p99，不只看平均值。
- 收益达到目标或明显超过噪声且复杂度合理时保留；否则只撤销本轮自己的优化。只有测量稳定、回归代价高时才增加性能 guard，避免把脆弱时间阈值塞进普通单元测试。
目标达到即停止。进一步优化进入 Deferred，不自动扩展范围。
低噪声约束
- 不默认生成性能报告、规划文档、TASK_GRAPH、worktree 或子 Agent。
- 不因缺少专用工具阻塞；先用项目已有能力，安装依赖或长时间压测需要明确收益和权限。
- 不用代码审美代替测量，也不把微小 benchmark 改善包装成用户价值。
- 性能变化破坏行为、数据、安全或可维护性时，不接受该优化。
输出
性能结果:
- 指标与负载: ...
- Baseline: ...
- 瓶颈与最小修改: ...
- After 与取舍: ...
- 正确性验证/剩余风险: ...
下一步建议: <一个具体动作>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 69 lines · 86 tokens per session scan A 3b3c6b6fd0fa
briefbound-performance-engineering is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 22d ago), licensed MIT. It adds 86 tokens to every session and 1,272 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
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
mcp-builder
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.