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/aayushostwal/nexus/performancenpx skills add aayushostwal/nexus --skill performancegit clone --depth 1 https://github.com/aayushostwal/nexusWhat 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 | $0.00068 | $0.00734 |
| Opus 5 | $0.00034 | $0.00367 |
| Sonnet 5 | $0.00014 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
nexus-performance 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nexus Performance
Route to the correct sub-skill and follow it end-to-end.
Compatibility
- Sub-skills:
memory-leak.md,dependency-blast-radius.md - Supporting files:
examples/production-scenarios.md,checklists/performance-checklist.md,heuristics/performance-heuristics.md,anti-patterns/common-mistakes.md,validation/output-validation.md - Required tools: Read, Bash, Grep
- Hands off to:
nexus:debuggingfor single-service runtime failures - Hands off to: the
roadmap-planneragent after the fix is approved
Routing
Step 1 — Classify the Request
Pick exactly one track:
| Track | Signal | Sub-skill |
|---|---|---|
| Memory Leak | "memory growing", "OOM kill", "heap dump", "RSS increasing", "memory usage creeping up", process being killed by the OS | memory-leak.md |
| Dependency Blast Radius | "upgrade X to version Y", "what breaks if I upgrade", "which services use this lib", "blast radius of upgrading", "safe to upgrade?", "dependency impact analysis" | dependency-blast-radius.md |
If the request does not clearly fit one track, ask one question: "Is this about memory/CPU/latency behavior of a running service, or about the risk of upgrading a dependency?"
Step 2 — Read Sub-Skill and Execute
Read the appropriate sub-skill file. Follow its numbered steps in order. Do not skip steps.
Read heuristics/performance-heuristics.md for fast pattern-matching before starting investigation.
Step 3 — Validate Output
Before presenting results, check against validation/output-validation.md.
Output Format
Each sub-skill defines its own output format. This router produces no standalone output.
Anti-Patterns
- Never profile a running production process without confirming the profiling overhead is acceptable.
- Never recommend a dependency upgrade without completing the blast radius analysis first.
- Never mix tracks — complete one sub-skill fully before considering another.
- Never skip reading the actual code or configuration — performance issues are almost always specific to the exact version and usage pattern.
- Never recommend "just increase memory/CPU limits" without first identifying the root cause — scaling a leak just delays the next OOM.
What ships with it
4 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.
- 3d ago First seen · 81 lines · 68 tokens per session scan A 6000871ccd1b
nexus-performance is a skill published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 734 once invoked, about $0.0003 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.
Other skills, from other repositories
productize-yourself
当用户在纠结职业/副业/自由职业方向、问「我该做什么才能赚钱/不被替代」、或想找到自己的独特优势时调用。 核心理念: 特殊知识(不可培训、对你像玩对别人像工作) × 产品化(杠杆规模化) = 无可替代的致富定位。 不适用于: 纯求职投递、写简历、已有明确方向的执行细节。 Triggers: 找方向/独特优势/副业/不可替代/productize/special knowledge/moat.
screen-detox
当用户刷手机/短视频/社交媒体上瘾、感觉空虚、想戒断多巴胺零食时调用。 核心理念: 所有屏幕活动与更少幸福相关(作者断言无例外); 屏幕=用长期后果换短期快感的多巴胺零食; 用习惯替换五步戒断。 不适用于: 工作需要屏幕的职业场景(区分工作屏幕与消费屏幕)。 Triggers: 刷手机/上瘾/短视频/社交媒体/多巴胺/戒断/屏幕时间/screen time/dopamine/addiction.
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
long-term-compounding
当用户在选择合作者/生意模式/人生策略、问「要不要长期投入这段关系/这个项目」「如何积累声誉」时调用。 核心理念: 财富、知识、声誉、关系都遵循复利; 只玩长期正和游戏, 与能想象共事一辈子的人合作, 拒绝短期思维交易。 不适用于: 紧急止损、短期现金周转等必须立即决策的场景。 Triggers: 长期/复利/声誉/合作/信任/compounding/long-term/trust.
monkey-mind-meditation
当用户脑子停不下来、焦虑反刍、想学冥想/提升专注力时调用。 核心理念: 内心独白(心猴)是失控程序不是"我"; 用调试模式逐条观察念头, 意识到即失去控制; 冥想=收件箱归零/心灵间歇性禁食。 不适用于: 严重精神疾病急性发作(先就医); 需要立刻处理的实际问题(先做事)。 Triggers: 冥想/焦虑/脑子停不下来/胡思乱想/专注/心猴/monkey mind/meditation/anxiety.
hook-craft
Specializes in chapter openings (hooks) and chapter endings (pulls). Every chapter must start with a reason to keep reading and end with a reason to turn the page. Runs after prose-craft, before chaos-engine. The skill that prevents the reader from putting the book down.