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/fergius-engineering/instincts/performance-at-scalenpx skills add Fergius-Engineering/instincts --skill performance-at-scalegit clone --depth 1 https://github.com/Fergius-Engineering/instinctsWrote 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/fergius-engineering/instincts/performance-at-scale)<a href="https://agentmods.dev/skills/fergius-engineering/instincts/performance-at-scale"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/performance-at-scale.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 | $0.00034 | $0.00461 |
| Opus 5 | $0.00017 | $0.00230 |
| Sonnet 5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
performance-at-scale 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.
What it actually says
The rule
Hot-path code meets your data at production scale, not at the handful of rows in your test fixture. A linear scan that's instant on ten items freezes the UI on a hundred thousand. The cost is invisible in the test and brutal in the field. Design the hot path for the largest realistic input before you write it, not after a user reports a freeze.
Fires when
Writing code that runs per item, per frame, or per event. Building a cache or a lookup. Iterating a collection that could grow large. Rebuilding a whole list when one entry changed.
How to apply
Before writing data-path code, ask "does this hold at the largest realistic input?"
Use O(1) lookups with an early exit — a map keyed by the thing you're asking about, so 99% of queries return immediately. Prefer incremental point updates (remove one, add one) over rebuilding the whole structure. Keep allocations and copies out of tight loops. Verbose logging in a hot loop is fine, but only after the early exit, never before it.
If the answer is "no, it won't scale", redesign before you write it, not after.
Worked example
A handler runs once per tile and scans a flat list of issues linearly to find the ones that match. With a dozen issues in the test, it's instant. In a real project the list holds four thousand issues, and every tile now costs a one-to-two second freeze. Keyed into a map by tile, each query early-exits in O(1) and the freeze is gone. The scan looked fine because the test never had enough data to make it hurt.
Red flags
| Thought | Reality |
|---|---|
| "It's fast enough" | Fast on the fixture, frozen at scale. |
| "I'll rebuild the whole list, it's simpler" | Simpler to write, O(N) to run every time. |
| "Just loop and find it" | A linear scan on a hot path is a freeze waiting for data. |
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 · 33 lines · 34 tokens per session scan A 2e8f6181e5eb
performance-at-scale is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 461 once invoked, about $0.0002 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
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
alipay-webhooks
Receive and verify Alipay (Antom / Alipay+) webhook notifications. Use when setting up Alipay webhook handlers, debugging RSA256 Signature header verification, or handling payment events like notifyPayment, notifyCapture, notifyRefund, notifyAuthorization, and notifyDispute.