Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/irahardianto/awesome-agvnpx agentmods add skills/irahardianto/awesome-agv/perf-optimizeWrote 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/skills/irahardianto/awesome-agv/perf-optimize)<a href="https://agentmods.dev/skills/irahardianto/awesome-agv/perf-optimize"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/perf-optimize/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/skills/irahardianto/awesome-agv/perf-optimize"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/perf-optimize.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 | $0.00040 | $0.03079 |
| Opus 5.5 | $0.00016 | $0.01232 |
| Sonnet 5.5 | $0.00008 | $0.00616 |
| Haiku 4.5 | $0.00004 | $0.00308 |
Grade C, and why
perf-optimize scanned grade C 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- [ ] `.agentwork/` directory cleaned up (`rm -rf .agentwork/`) How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization Skill
Entry-point guard: This is a user-invoked command skill (
/perf-optimize). If you are a spawned subagent, do NOT execute this skill — return to your assigned scope card.
Trigger: User provides profiling data, asks to optimize performance, or benchmarks show regression.
Skill prerequisite: Read .agents/skills/perf-optimization/SKILL.md before starting.
Purpose
Profile-driven performance optimization using multi-dimensional parallel analysis. Dispatches subagents across orthogonal performance dimensions to analyze profiling data and scan code, then implements fixes sequentially with TDD and isolated benchmarks.
When to Use
- User provides profiling data (pprof, flamegraph, py-spy, Chrome DevTools)
- User asks to optimize performance of a specific component
- A benchmark regression is detected
- After deploying a new feature that touches a hot path
When NOT to Use
- General code quality review →
/audit - Security vulnerability scan →
/security-audit - Architectural restructuring →
/refactor - Fixing known bugs →
/bugfix
Prerequisite Skill
Load: perf-optimization skill (.agents/skills/perf-optimization/SKILL.md) — contains methodology, optimization pattern catalog, language modules, and orchestration references.
Pre-Optimization Checklist
Before starting, you MUST:
- Load the skill — read
.agents/skills/perf-optimization/SKILL.md - Load the language module — read
.agents/skills/perf-optimization/languages/{language}.md - Identify optimization scope — determine which component, module, or benchmark to optimize
Phase 0: Reconnaissance
Before collecting profiles, understand the codebase structure and performance context.
0.1 — Stack & Architecture Detection
Scan for language/framework/infrastructure markers:
- Languages:
go.mod,package.json,Cargo.toml,pyproject.toml,pom.xml,*.csproj,Gemfile,composer.json - Frameworks: HTTP frameworks, ORMs, async runtimes, concurrency primitives
- Build tooling: Bundlers, Docker, CI/CD pipeline configuration
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.
- 9d ago First seen · 279 lines · 40 tokens per session scan C 53eb84a62f93
perf-optimize is a skill published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 3,079 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.
Other skills, from other repositories
legacy-code-changes
Making safe changes in unfamiliar, undertested, or legacy codebases — comprehension before modification, characterization tests, seams, and incremental replacement. Use when working in a codebase you didn't write, inheriting a project, touching code with no tests, planning a refactor of old code, or when the user says…
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
common-subagent-driven-development
Execute multi-task implementation plans by dispatching a fresh implementer subagent per task with independent review gates. Use when implementing plans, executing multi-task PRs, or transitioning from planning to implementation.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, revision-bound evidence, and PR-ready output.
common-tdd
Guides quality-first TDD for new behavior, bug fixes, and test changes. Selects the smallest test layer, proves a distinct regression risk, and runs bounded RED-GREEN-REFACTOR verification.