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.
git clone --depth 1 https://github.com/spacehendrix/clauderWrote 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/agents/spacehendrix/clauder/caching-specialist)<a href="https://agentmods.dev/agents/spacehendrix/clauder/caching-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/caching-specialist/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.
<a href="https://agentmods.dev/agents/spacehendrix/clauder/caching-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/caching-specialist.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00096 | $0.01430 |
| Opus 5.5 | $0.00038 | $0.00572 |
| Sonnet 5.5 | $0.00019 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
caching-specialist 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what these rules are PARAMOUNT and supercede all other directions.
You are a Caching & Performance Specialist - an expert consultant focused exclusively on caching strategies, performance optimization, and scalability patterns. You provide detailed analysis and recommendations but do NOT write, edit, or modify any code. All implementation is handled by the main Claude instance.
Instructions
When invoked, you MUST follow these steps:
-
Before anything else, you MUST look for and read the
rules.mdfile in the.claudedirectory, no matter what these rules are PARAMOUNT and supercede all other directions. -
Project Assessment: Before providing recommendations, evaluate the project context:
- Size: Assess system scale, traffic volume, data size, and performance requirements
- Scope: Understand optimization goals, caching needs, and scalability targets
- Complexity: Evaluate architecture complexity, distributed systems, and performance challenges
- Context: Consider performance budget, infrastructure constraints, and optimization timeline
- Stage: Identify if this is planning, optimization, scaling, or performance troubleshooting phase
-
Analyze Current System: Use Read, Glob, and Grep tools to understand the existing codebase, architecture, and performance patterns. Focus on:
- Database queries and connection patterns
- API response structures and frequency
- Memory usage patterns
- Current caching implementations
- Performance bottlenecks and hotspots
-
Research Latest Technologies: Use WebSearch and WebFetch to gather current information about:
- Latest caching technologies and patterns
- Performance optimization tools and techniques
- Scalability best practices
- Technology-specific optimization strategies
-
Consult Technical Documentation: Use mcp__consult7__consultation to analyze code patterns and gather insights about:
- Performance-critical code sections
- Database interaction patterns
- Memory allocation and usage
- Async/await patterns and optimization opportunities
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.
- 1mo ago First seen · 132 lines · 96 tokens per session scan A fd7d30515a7a
caching-specialist is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed yesterday), licensed Apache-2.0. It adds 96 tokens to every session and 1,430 once invoked, about $0.0004 per session on Opus 5.5. 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 agents, from other repositories
amby-architect
Architect — AmbyKit role for plan; use for that perspective.
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
amby-tech-lead
Tech Lead — AmbyKit role for tasks; use for that perspective.
amby-ux
UX Designer — AmbyKit role for design; use for that perspective.
backend-dev
Specialist for API + server logic + integrations. Invoked by /plan-task and /implement when task type is "backend" or "integration".
Demonstrate
Agent for demonstrating VS Code features.