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 commands/vladolaru/claude-code-plugins/optimize-imagesgit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWhat 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 | $0.00018 | $0.00724 |
| Opus 5 | $0.00009 | $0.00362 |
| Sonnet 5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
optimize-images 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Asset Optimizer
Lossless image optimization with review -> confirm -> apply workflow.
Target: $ARGUMENTS (directory or image file to optimize)
How It Works
Raster images (PNG, JPEG, GIF): Optimizations are fully lossless - file sizes are reduced without any loss in image quality. Uses ImageOptim which applies multiple optimization techniques while preserving every pixel.
SVG files: Uses svgo, the same optimizer powering SVGOMG. The bundled configuration uses web-safe default techniques that safely reduce file size without breaking SVG rendering.
Prerequisites
# Raster images (PNG, JPEG, GIF)
npm install -g imageoptim-cli
# ImageOptim.app required: https://imageoptim.com
# SVG optimization
npm install -g svgo
Workflow (MUST FOLLOW)
Step 1: Optimize and Show Report
Run optimization WITHOUT --cleanup to generate and review results:
"${CLAUDE_PLUGIN_ROOT}/scripts/optimize-images.sh" "$ARGUMENTS" "${CLAUDE_PLUGIN_ROOT}/scripts/svgo.config.mjs" /tmp/img-optimize
Answer N when prompted. This preserves the temp directory.
Step 2: Ask User for Confirmation
REQUIRED: After showing the report, ASK THE USER if they want to apply the optimizations. Do NOT proceed without explicit user confirmation.
Step 3: Apply or Cancel (with cleanup)
Based on user's answer, run WITH --cleanup:
If user confirms YES:
echo "y" | "${CLAUDE_PLUGIN_ROOT}/scripts/optimize-images.sh" --cleanup "$ARGUMENTS" "${CLAUDE_PLUGIN_ROOT}/scripts/svgo.config.mjs" /tmp/img-optimize
If user says NO:
echo "n" | "${CLAUDE_PLUGIN_ROOT}/scripts/optimize-images.sh" --cleanup "$ARGUMENTS" "${CLAUDE_PLUGIN_ROOT}/scripts/svgo.config.mjs" /tmp/img-optimize
Both commands clean up the temp directory. The --cleanup flag ensures cleanup happens regardless of yes/no.
Quick Reference
| Option | Description |
|---|---|
--cleanup |
Clean up temp directory when done (always cleans up on exit) |
--help |
Show usage information |
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.
- 2d ago First seen · 86 lines · 18 tokens per session scan A 0a03068caac5
optimize-images is a command published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 724 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.