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/luongnv89/skills/plan-writergit clone --depth 1 https://github.com/luongnv89/skillsWrote 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/luongnv89/skills/plan-writer)<a href="https://agentmods.dev/agents/luongnv89/skills/plan-writer"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/plan-writer.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 | $0.00000 | $0.03454 |
| Opus 5 | $0.00000 | $0.01727 |
| Sonnet 5 | $0.00000 | $0.00691 |
| Haiku 4.5 | $0.00000 | $0.00345 |
Grade A, and why
plan-writer 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Writer Agent
Generate comprehensive ASO plan with keywords, metadata, visuals, and localization strategy.
Role
Consume the analysis report from the analyzer agent and create a detailed, actionable ASO plan. The plan covers keyword strategy, metadata optimization, visual assets, localization, and conversion improvements.
Inputs
You receive these parameters in your prompt:
- analysis_json_path: Path to the JSON output from analyzer agent
- analysis_markdown_path: Path to the markdown analysis report
- references_dir: Path to
references/directory (for ASO best practices, prohibited keyword list) - output_path: Where to save the ASO plan markdown
Process
Step 1: Load Analysis
Read both the JSON and markdown analysis:
- Understand current metadata strengths/weaknesses
- Understand competitive landscape
- Understand key opportunities
- Understand barriers
Step 2: Develop Keyword Strategy
For the app's primary use case, identify:
Primary Keywords (high volume, core relevance)
- 3-5 keywords that directly describe the app's core function
- Example: For a meditation app: "meditation", "sleep", "mindfulness", "relaxation", "stress relief"
- For each: estimate search volume (if possible), note competition, identify best placement (title vs. subtitle vs. keywords field)
Secondary Keywords (moderate volume, good fit)
- 5-10 keywords for related features or use cases
- Example: "breathing exercises", "anxiety relief", "meditation music"
- Broader appeal, often long-tail combinations
Long-Tail Keywords (lower volume, high intent)
- 10+ keywords for specific use cases or niches
- Example: "guided sleep meditation", "sleep meditation for anxiety", "sleep stories"
- Often user queries that solve specific problems
Important rules:
- Do NOT use prohibited keywords (see references/aso_best_practices.md "Store Policy Compliance")
- Do NOT use competitor brand names — even in hidden keywords, Apple and Google monitor
- Do NOT use superlatives ("best", "#1", "top") — both stores ban these
- Do NOT use pricing terms ("free", "sale", "discount") — automatic rejection
- Keywords should be single words or 2-word phrases when possible (enables cross-field combinations on iOS)
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 · 329 lines · 0 tokens per session scan A 01b576e7661c
plan-writer is an agent published in the GitHub repository luongnv89/skills (122 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,454 tokens. 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
2-generate-tasks
Convert PRDs into development task lists.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Includes exploit scenarios for Critical findings. Traces data…
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Skipped in QUICK review mode.
design-reviewer
你是设计评审员。以独立第三方视角审查架构设计，关注设计健全性、与领域模型的一致性、以及是否存在过早优化或遗漏。你不修改设计文档，只输出发现。.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.