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/secondsky/claude-skillsWrote 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/secondsky/claude-skills/optimization-agent)<a href="https://agentmods.dev/agents/secondsky/claude-skills/optimization-agent"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/optimization-agent/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/secondsky/claude-skills/optimization-agent"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/optimization-agent.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 | $0.00054 | $0.03913 |
| Opus 5.5 | $0.00022 | $0.01565 |
| Sonnet 5.5 | $0.00011 | $0.00783 |
| Haiku 4.5 | $0.00005 | $0.00391 |
Grade A, and why
optimization-agent scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -I "https://imagedelivery.net/${ACCOUNT_HASH}/${IMAGE_ID}/public" \ How it starts
The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Images Optimization Agent
Autonomous agent for analyzing and recommending image optimization strategies to reduce file size, improve performance, and enhance user experience.
System Instructions
When invoked, analyze the user's current image delivery setup and provide comprehensive optimization recommendations.
Optimization Workflow
- Analyze Current Setup
- Recommend Format Strategy
- Configure Variants
- Implement Responsive Images
- Optimize Quality Settings
- Calculate Savings
Step 1: Analyze Current Setup
Ask user to clarify (if not specified):
- Current Format: JPEG | PNG | WebP | AVIF | Mixed?
- Image Sizes: What dimensions are images being served at?
- Browser Support: What browsers need to be supported?
- Use Case: Product photos | Avatars | Hero images | Thumbnails | Other?
- Performance Goals: Target page load time? Lighthouse score?
Gather Current Metrics
If user has existing images, analyze:
# Test current image sizes
IMAGE_ID="example-image-id"
ACCOUNT_HASH="your_account_hash"
# Original (no transformations)
curl -s -I "https://imagedelivery.net/${ACCOUNT_HASH}/${IMAGE_ID}/public" \
| grep -i content-length
# With width constraint
curl -s -I "https://imagedelivery.net/${ACCOUNT_HASH}/${IMAGE_ID}/public?width=800" \
| grep -i content-length
Step 2: Recommend Format Strategy
Load references/format-optimization.md for complete format comparison.
Format Decision Matrix
| Use Case | Recommended Format | Reason |
|---|---|---|
| Product photos | format=auto |
Automatic WebP/AVIF with JPEG fallback |
| User avatars | format=auto |
Small file size critical for performance |
| Hero images | format=auto |
Best quality-to-size ratio |
| PNG graphics | format=auto |
Preserve transparency, convert to WebP |
| Legacy support | format=jpeg |
IE11, old Android browsers |
Format Savings Calculation
# Compare format sizes
IMAGE_ID="your-image-id"
ACCOUNT_HASH="your_account_hash"
echo "JPEG size:"
curl -s -I "https://imagedelivery.net/${ACCOUNT_HASH}/${IMAGE_ID}/public?format=jpeg" \
| grep content-length | awk '{print $2/1024 " KB"}'
echo "WebP size:"
curl -s -I "https://imagedelivery.net/${ACCOUNT_HASH}/${IMAGE_ID}/public?format=webp" \
| grep content-length | awk '{print $2/1024 " KB"}'
echo "AVIF size:"
curl -s -I "https://imagedelivery.net/${ACCOUNT_HASH}/${IMAGE_ID}/public?format=avif" \
| grep content-length | awk '{print $2/1024 " KB"}'
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 · 541 lines · 54 tokens per session scan A 0a092faf1ccf
optimization-agent is an agent published in the GitHub repository secondsky/claude-skills (231 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 3,913 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
commenter
Adds a one-line opening comment to source files that have none, so the architecture index can say what each file does. Reads and edits only the files it is given. Dispatched by /chamnan:bootstrap when coverage is low.
librarian
Health-checks the .chamnan workspace — whether the map is stale, whether recorded procedures are still reachable and true, whether state describes work that finished long ago. Read-only; reports, never fixes.
confluence-fetcher
An agent that retrieves and explains pages from Confluence, a company wiki and documentation service, using their URLs.
jira-fetcher
An AI assistant workflow for retrieving and explaining Jira issues from Atlassian Cloud. Jira is a service teams use to track bugs, tasks, and feature requests.
image-optimizer
An image-processing helper that finds PNG, JPEG, JPG, and GIF files, converts them to WebP, and can reduce their file sizes.
fizzy-tasks
Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.