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 skills/konamgil/mandu/mandu-performancenpx skills add konamgil/mandu --skill mandu-performancegit clone --depth 1 https://github.com/konamgil/manduWrote 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/konamgil/mandu/mandu-performance)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-performance"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-performance.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 5.1 | $0.00049 | $0.00958 |
| Opus 5 | $0.00024 | $0.00479 |
| Sonnet 5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
mandu-performance 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 6d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Performance
Mandu 애플리케이션의 성능 최적화 가이드. 워터폴 제거, 번들 최적화, 캐싱 패턴, Bun 런타임 활용법을 다룹니다. Vercel의 React Best Practices를 Mandu 컨텍스트로 변환하여 적용합니다.
Agent Workflow Contract
This skill is a Domain addendum. It must not replace mandu-agent-workflow.
Use it only after mandu.agent.plan selects performance, hydration, route, API, or runtime domains.
Canonical workflow step: plan -> verify -> repair.
Preferred MCP tools:
| Step | Tools |
|---|---|
| plan | mandu.agent.plan, mandu.agent.context |
| apply | mandu.agent.apply |
| verify | mandu.agent.verify, mandu.build, mandu.run.tests |
| repair | mandu.agent.repair |
Allowed file edits:
- Route, slot, island, or cache code named in the plan
- Import boundaries that reduce bundle/runtime cost
- Benchmark/test files scoped to the performance claim
Verification command:
mandu agent verify --changed --json --write
Common failures:
- Optimizing without a measurable route, bundle, or runtime target
- Moving server-only code into client islands for convenience
- Skipping typecheck or targeted tests after cache/import rewrites
Repair path:
mandu agent repair --from .mandu/agent-verify.json --json
When to Apply
Reference these guidelines when:
- Optimizing slot handler response times
- Reducing Island component bundle size
- Implementing caching strategies
- Working with async/await patterns
- Leveraging Bun runtime features
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Async Optimization | CRITICAL | perf-async- |
| 2 | Bundle Optimization | CRITICAL | perf-bundle- |
| 3 | Caching Strategies | HIGH | perf-cache- |
| 4 | Bun Runtime | HIGH | perf-bun- |
| 5 | Rendering | MEDIUM | perf-render- |
Quick Reference
1. Async Optimization (CRITICAL)
perf-async-parallel- Use Promise.all() for independent operationsperf-async-defer-await- Move await into branches where actually usedperf-async-early-start- Start promises early, await late
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- metadata.json 794 B
- rules/_sections.md 1.3 KB
- rules/_template.md 1.4 KB
- rules/perf-async-defer-await.md 2.5 KB
- rules/perf-async-parallel.md 2.6 KB
- rules/perf-bun-file.md 3.0 KB
- rules/perf-bun-serve.md 2.5 KB
- rules/perf-bundle-imports.md 2.2 KB
- rules/perf-bundle-island-lazy.md 3.0 KB
- rules/perf-cache-react.md 2.6 KB
- rules/perf-render-transitions.md 3.5 KB
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.
- 6d ago First seen · 126 lines · 49 tokens per session scan A 3691b76a0943
mandu-performance is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 10d ago), licensed MPL-2.0. It adds 49 tokens to every session and 958 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 skills, from other repositories
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
truecourse-list
List TrueCourse violations found in this repository.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
flash-reel
Generates a 30-second 9 16 cinematic reel from a user prompt (setting + vibe + rough storyline). Flash Reel — 30s Cinematic Reel Skill When to use User provides: a setting, a vibe/mood, and optionally a rough storyline. They want a 30 second 9:16 reel with hard cuts every 3-4 seconds, anchored by one or more…
seedance-prompting-skills-for-cinematic-films
When to use Trigger this skill when the user requests photorealistic cinematic motion — not stylized animation, not motion design, not UGC. Specifically.