developer-performance-instincts

developer-performance-instincts is a skill for Claude Code from iampantherr/SecureContext. It costs 20 tokens per session (500 once invoked), scanned A, original, MIT.

A collection of software performance guidelines covering measurement, algorithm efficiency, databases, and caching. Caching stores reused results so later requests can be served faster.

In plain words
What is it for?
Use it to profile applications, assess algorithm costs, inspect database query plans, find N+1 queries, batch operations, manage connection pools, and choose cache layers.
Why use it?
It replaces guesswork with measurement and highlights common causes of slow applications, such as inefficient loops, unindexed queries, repeated database calls, and poorly managed caches.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zc-ctx plugin — 27 skills shipped together

Good fit Use it to profile applications, assess algorithm costs, inspect database query plans, find N+1 queries, batch operations, manage connection pools, and choose cache layers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iampantherr/securecontext/developer-performance-instincts
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 iampantherr/SecureContext --skill developer-performance-instincts
Clone the repo
git clone --depth 1 https://github.com/iampantherr/SecureContext

Made for: Claude Code.

Or install zc-ctx, the plugin that ships this one along with the rest of its 27 skills.

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 developer-performance-instincts

README.md
[![agentmods](https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-performance-instincts/github.svg)](https://agentmods.dev/skills/iampantherr/securecontext/developer-performance-instincts)
Your own site
<a href="https://agentmods.dev/skills/iampantherr/securecontext/developer-performance-instincts"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-performance-instincts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for developer-performance-instincts

Your own site · 80×15
<a href="https://agentmods.dev/skills/iampantherr/securecontext/developer-performance-instincts"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-performance-instincts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 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 $0.00020 $0.00500
Opus 5 $0.00010 $0.00250
Sonnet 5 $0.00004 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured yesterday against content hash 3d3ca8bacefc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

developer-performance-instincts 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 yesterday.

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.

skills/_staging_v0_19/developer-performance-instincts.skill.md · 36 lines

What it actually says

PERFORMANCE INSTINCTS

(Extracted from roles.json deepPrompt for the developer role during the v0.19.0 role/skill split. Original content preserved verbatim. Edit freely; the mutator will propose improvements based on skill_runs telemetry once this skill is invoked by an agent.)


Measure First: Never guess at performance. Profile in production or with production-representative data. console.log timing and Chrome DevTools performance tab are enough to locate 80% of perf problems.

Big-O Awareness: Know the complexity of your data structures. Understand that O(n²) in a loop over user data is fine for 10 users and catastrophic at 10,000. O(n log n) sort before a comparison is almost always correct. O(n) linear scan through a hash set boundary is a bug.

Database Performance: Indexes are the highest-leverage performance tool. Understand query plans (EXPLAIN ANALYZE). Identify N+1s with query logging in development. Batch operations where possible. Connection pooling is not optional in production.

Caching: Cache at the layer closest to the consumer (HTTP cache headers, CDN, Redis, in-process). Every cache layer adds a staleness problem. Prefer idempotent, immutable URLs that can be cached forever (content-addressed assets) over cached mutable data.

Frontend Performance: Largest Contentful Paint and Time to Interactive are the user-facing metrics that matter. Lazy-load routes and heavy components. Prefer fewer, larger bundles over many small ones for most apps. Tree-shake aggressively. Never ship unused CSS.


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. yesterday First seen · 36 lines · 20 tokens per session scan A 3d3ca8bacefc

Subscribe to this mod's changes

developer-performance-instincts is a skill published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 500 once invoked, about $0.0001 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 2026-09-08.

Related

Other skills, from other repositories