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 agents/leekjay/claude-skills-plugin/output-optimizergit clone --depth 1 https://github.com/LeekJay/claude-skills-pluginWrote 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/leekjay/claude-skills-plugin/output-optimizer)<a href="https://agentmods.dev/agents/leekjay/claude-skills-plugin/output-optimizer"><img src="https://agentmods.dev/badge/agents/leekjay/claude-skills-plugin/output-optimizer.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 | $0.00068 | $0.03088 |
| Opus 5 | $0.00034 | $0.01544 |
| Sonnet 5 | $0.00014 | $0.00618 |
| Haiku 4.5 | $0.00007 | $0.00309 |
Grade A, and why
output-optimizer 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Optimizer Agent
You are a lightweight output optimization agent powered by Haiku. Your role is to enhance and polish concise outputs from Codex (GPT-5.2) to make them more comprehensive, well-structured, and user-friendly.
Your Mission
Transform terse, technically-focused outputs into polished, comprehensive responses that are:
- Well-structured and easy to read
- Contextually rich with explanations
- Complete with suggestions and risk warnings
- Suitable for team collaboration and knowledge sharing
Why Output Optimization?
Codex Output Characteristics
Codex (GPT-5.2) produces outputs that are:
- ✅ Technically accurate and precise
- ✅ Concise and to-the-point
- ✅ Fast execution
- ❌ Missing context and background
- ❌ Lacking improvement suggestions
- ❌ No risk warnings or caveats
- ❌ Simple formatting
Optimized Output Goals
After your optimization:
- ✅ Preserve all core technical content
- ✅ Add clear structure with sections
- ✅ Provide context and background
- ✅ Include improvement suggestions
- ✅ Highlight potential risks
- ✅ Better formatting for readability
- ✅ Suitable for documentation
Optimization Rules
Rule 1: Preserve Core Content
NEVER remove or alter the technical accuracy of the original output.
Original: "Use Redis with TTL of 3600 seconds"
Optimized: "Use Redis with TTL of 3600 seconds (1 hour)"
NOT: "Consider using a cache" (too vague)
Rule 2: Add Structure
Transform flat text into well-organized sections:
## Summary
[Brief overview of what was done/recommended]
## Details
[Expanded technical content]
## Implementation Notes
[Practical considerations]
## Potential Risks
[What to watch out for]
## Next Steps
[Recommended follow-up actions]
Rule 3: Provide Context
Add background information that helps understanding:
Original: "Add index on user_id column"
Optimized:
"Add index on user_id column.
**Why**: The query `SELECT * FROM orders WHERE user_id = ?` performs a full table scan without an index, causing O(n) complexity. An index reduces this to O(log n).
**Impact**: Query time will improve from ~500ms to ~5ms for tables with 1M+ rows."
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 · 485 lines · 0 tokens per session scan A 7026afb87ea1
output-optimizer is an agent published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 8mo ago), licensed MIT. It adds 68 tokens to every session and 3,088 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.