EngineeringPROPRO REQUIREDFC-ENG-009
Performance Claw
perf-claw
v0.2.0May 22, 2026Performance profiling — bottleneck identification, flame graphs, and optimization with real benchmarks, not guesses
Performance work without a baseline and a target is just guessing with a profiler. I instrument the critical path, establish p50/p95/p99 latency budgets, identify the bottleneck that actually moves the needle, and measure again — because the second-biggest bottleneck is always the one you didn't find yet.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
Unlock with ProCOMPATIBLE WITH
OpenClawHermesClaude CodeCodex+4
8 compatible tools3 output formats
When to Use
- Implement production-grade code and architecture
- Audit design decisions and tradeoffs
- Catch reliability issues before release
- Raise quality consistency across teams
Compatible Frameworks
OpenClawHermesClaude CodeCodexCursorWindsurfAiderOllama8 TOOLS
Quality Gates
- Bottlenecks identified with profiling data
- Measurable improvements with before/after metrics
- Caching with invalidation strategies
- Performance budgets defined
- Trade-offs documented
3 GATES DEFINED
Expected Outputs
Performance Audit Report with Bottleneck Flame GraphsLatency Budget Specification (p50/p95/p99 per Endpoint)Optimized Implementation with Before/After Benchmark Comparison
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/perf-claw/SKILL.mdhermes/skills/flickclaw/perf-claw/references/workflow.mdhermes/skills/flickclaw/perf-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/perf-claw/SKILL.mdclaude-code/.claude/skills/perf-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/perf-claw/codex.mdcodex/.flickclaw/agents/perf-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-perf-claw.mdccursor/.cursor/rules/flickclaw-perf-claw-workflow.mdccursor/.cursor/rules/flickclaw-perf-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-perf-claw.mdwindsurf/.windsurf/rules/flickclaw-perf-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-perf-claw-quality-gates.mdAider3 files
aider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlOllama4 files
ollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
OpenClaw
npm exec --yes @flickclaw/cli@latest -- install perf-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Performance Claw to see what it can do:
Review the codebase architecture and identify 3 areas for improvement. Focus on maintainability, test coverage, and performance. Produce Performance Audit Report with Bottleneck Flame Graphs, Latency Budget Specification (p50/p95/p99 per Endpoint), Optimized Implementation with Before/After Benchmark Comparison.Example Output
IllustrativeWhat a typical Performance Claw report looks like:
# Performance Claw — Assessment Report **Project**: mobile-backend **Context**: a GraphQL API serving React Native clients with offline sync **Generated**: 2026-07-10 ## Executive Summary The Performance Claw completed its review of mobile-backend (a GraphQL API serving React Native clients with offline sync). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P1** | Schema | Over-fetching on timeline query (50+ fields) | Add field-level resolution and DataLoader batching | | 2 | **P2** | Error handling | Mutations return 500 without detail | Add typed error codes and user-friendly messages | | 3 | **P2** | Caching | No cache headers on static responses | Add ETag and Cache-Control for query results | ## Quality Gates - [✓] performance_baseline_measured_with_p50_p95_and_p99_latencies - [✓] bottleneck_identified_with_flame_graph_or_tracing_evidence - [✓] optimization_validated_with_before_and_after_benchmark_data ## Outputs Generated - **Performance Audit Report with Bottleneck Flame Graphs**: Included in the report above. - **Latency Budget Specification (p50/p95/p99 per Endpoint)**: Included in the report above. - **Optimized Implementation with Before/After Benchmark Comparison**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 3 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*
RELATED AGENTS