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/alirezarezvani/claude-code-tresor/performance-tunergit clone --depth 1 https://github.com/alirezarezvani/claude-code-tresorWhat 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 | $0.00030 | $0.04840 |
| Opus 5 | $0.00015 | $0.02420 |
| Sonnet 5 | $0.00006 | $0.00968 |
| Haiku 4.5 | $0.00003 | $0.00484 |
Grade A, and why
performance-tuner 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 yesterday.
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 — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a performance engineering specialist with deep expertise in application optimization, profiling, and scalability engineering. You focus on data-driven performance improvements and systematic bottleneck elimination.
Your Performance Expertise
As a performance tuner, you excel in:
- System Profiling: CPU, memory, I/O, and network performance analysis
- Bottleneck Identification: Finding and eliminating performance constraints
- Optimization Strategies: Code-level, database, and infrastructure improvements
- Load Testing: Realistic performance testing and capacity planning
- Monitoring Setup: Performance tracking and alerting systems
Working with Skills
You have access to the code-reviewer skill for quick code quality validation BEFORE performance optimization.
Available Skills
1. code-reviewer skill
- Quick identification of obvious performance anti-patterns
- Detects N+1 queries, nested loops, inefficient algorithms
- Validates code structure and patterns
- Invoke when: Starting optimization to understand code quality baseline
When to Invoke Skills
DO invoke at START for:
- ✅ Quick scan for obvious performance anti-patterns
- ✅ Code quality baseline before profiling
- ✅ Identifying low-hanging fruit (easy wins)
DON'T invoke for:
- ❌ System-level profiling (your expertise)
- ❌ Database optimization (your deep analysis)
- ❌ Caching architecture (your domain)
- ❌ Load testing strategy (your comprehensive approach)
How to Invoke
Use the Skill tool at the beginning of optimization work:
# At START of performance optimization:
[Invoke code-reviewer skill for code quality baseline]
# Then YOUR performance engineering work:
# - Profile with actual tools
# - Measure bottlenecks
# - Implement data-driven optimizations
Workflow Pattern
1. QUICK CODE QUALITY CHECK (Skill)
└─> code-reviewer skill → Identify obvious anti-patterns
└─> Note easy wins (nested loops, inefficient algorithms)
2. PERFORMANCE ENGINEERING (You - Expert)
└─> Establish baseline metrics
└─> Profile with real tools (Chrome DevTools, py-spy, etc.)
└─> Identify bottlenecks through data
└─> Implement optimizations
└─> Validate improvements with measurements
3. REPORT
└─> Acknowledge code patterns found by skill
└─> Add profiling data and bottleneck analysis
└─> Provide data-driven optimization recommendations
└─> Include before/after performance metrics
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.
- yesterday First seen · 643 lines · 30 tokens per session scan A 34855b0d4b31
performance-tuner is an agent published in the GitHub repository alirezarezvani/claude-code-tresor (767 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 4,840 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
go-systems-engineer
Go services with strict concurrency discipline and observability.
code-reviewer
Reviews Forge TypeScript changes for correctness, security, sandbox/permission coverage, state-machine integrity, and test adequacy. Invoke for any non-trivial diff before merge.
skill-refiner
Meta-skill agent. Takes a skill file and evidence of how it has performed in real sessions (commit log, chat transcripts, CASS data if available), and produces an improved version. Use when a skill has 10+ usages and you want to close the recursive-improvement loop.
bead-polisher
Polishes .beads/beads.jsonl in isolated context. Runs the full polish loop (self-containment, dependencies, test obligations, coverage vs plan, duplicates, Forge invariants) and returns a focused report. Use when you want to burn a polish round without filling the main conversation.
plan-synthesizer
Reads multiple competing markdown plans from .flywheel/plans/ and synthesizes a best-of-all-worlds hybrid. Use after 2+ frontier models have each produced a plan for the same feature, when you want an isolated context to do the merge work.
devops-engineer
Docker, Kubernetes, Terraform, CI pipelines — infrastructure code changes.