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/jhlee0409/claude-plugins/cache-managernpx skills add jhlee0409/claude-plugins --skill cache-managergit clone --depth 1 https://github.com/jhlee0409/claude-pluginsWrote 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/jhlee0409/claude-plugins/cache-manager)<a href="https://agentmods.dev/skills/jhlee0409/claude-plugins/cache-manager"><img src="https://agentmods.dev/badge/skills/jhlee0409/claude-plugins/cache-manager.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 | $0.00011 | $0.01660 |
| Opus 5 | $0.00005 | $0.00830 |
| Sonnet 5 | $0.00002 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade A, and why
cache-manager 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cache Manager Skill
분석 결과를 캐시하여 증분 검증을 지원합니다.
WHEN TO USE
This skill is invoked by:
/fsdarch:analyze- To enable incremental analysis/fsdarch:validate- To speed up validation
EXECUTION INSTRUCTIONS
Step 1: Check Cache Existence
Action: Check if cache file exists
1. Use Glob to check for .fsd-architect.cache.json
2. If not found → return { valid: false, reason: 'no-cache' }
3. If found → proceed to Step 2
Glob command:
Glob: ".fsd-architect.cache.json"
Step 2: Validate Cache
Action: Read and validate cache integrity
1. Read .fsd-architect.cache.json using Read tool
2. Parse JSON (handle parse errors → E501)
3. Check version field matches current plugin version
4. Compute hash of .fsd-architect.json
5. Compare with cached configHash
Read commands:
Read: .fsd-architect.cache.json
Read: .fsd-architect.json # For hash comparison
Hash Function Implementation:
/**
* Simple string hash function for config comparison.
* Produces a consistent hash for cache invalidation detection.
*/
function simpleHash(content: string): string {
let hash = 0;
for (let i = 0; i < content.length; i++) {
const char = content.charCodeAt(i);
hash = ((hash << 5) - hash) + char;
hash = hash & hash; // Convert to 32bit integer
}
// Convert to base-36 for compact representation
return Math.abs(hash).toString(36);
}
Validation checks:
// Version check
if (cache.version !== '1.0.0') {
return { valid: false, reason: 'version-mismatch' }; // E503
}
// Config hash check using simpleHash()
const currentConfig = await read('.fsd-architect.json');
const currentHash = simpleHash(currentConfig);
if (cache.configHash !== currentHash) {
return { valid: false, reason: 'config-changed' };
}
// Age check (24 hours = 86400000 ms)
if (Date.now() - cache.timestamp > 86400000) {
return { valid: false, reason: 'expired' };
}
interface CacheFile {
version: string;
configHash: string;
timestamp: number;
layers: LayerCache;
files: FileCache;
}
interface LayerCache {
[layerName: string]: {
path: string;
slices: string[];
lastModified: number;
};
}
interface FileCache {
[filePath: string]: {
mtime: number;
imports: string[];
violations: Violation[];
};
}
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 · 294 lines · 11 tokens per session scan A 9b54d87e1c70
cache-manager is a skill published in the GitHub repository jhlee0409/claude-plugins (4 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 1,660 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 2026-08-31.
Other skills, from other repositories
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
preserved_skill
previous skill.
performing-api-fuzzing-with-restler
Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.