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/reviewergit 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/reviewer)<a href="https://agentmods.dev/agents/luongnv89/skills/reviewer"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/reviewer.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 | $0.00000 | $0.03775 |
| Opus 5 | $0.00000 | $0.01887 |
| Sonnet 5 | $0.00000 | $0.00755 |
| Haiku 4.5 | $0.00000 | $0.00378 |
Grade A, and why
reviewer 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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Agent
Final quality review of ASO implementation against best practices.
Role
Fresh-context review of the ASO implementation (Phase 5 review checklist + Phase 6 best-practices verification). Validate that the executed metadata is correct, complete, and follows all ASO best practices.
Inputs
You receive these parameters in your prompt:
- project_dir: Root directory of the mobile app project
- implementation_summary_path: Path to the implementation summary from executor
- original_plan_path: Path to the approved ASO plan
- references_dir: Path to
references/aso_best_practices.md - output_path: Where to save the review report
Process
Step 1: Load Context
Read:
- The original ASO plan (what was approved)
- The implementation summary (what was executed)
- The actual metadata files in the project directory
- The best practices reference
Step 2: Phase 5 Review Checklist
Verify all executed metadata against the review checklist:
## Phase 5 Review Checklist
- [ ] All metadata fields within character limits
- iOS: Name ≤ 30, Subtitle ≤ 30, Keywords ≤ 100, Description ≤ 4000, What's New ≤ 4000
- Android: Title ≤ 30, Short ≤ 80, Full ≤ 4000
- [ ] No keyword duplication across indexed fields (iOS)
- Keywords field does NOT contain words from Name or Subtitle
- Example: Name "Meditation Sleep", Subtitle "Better", Keywords should not contain "meditation", "sleep", or "better"
- [ ] Keywords field properly formatted (commas, no spaces)
- Format: "word1,word2,word3" (no spaces after commas)
- Verified: [YES/NO]
- [ ] Descriptions read naturally with keywords integrated
- Keywords appear 3-5 times naturally (not stuffed)
- Readability score: [check by reading]
- Example sentences flow naturally: [YES/NO]
- [ ] No spelling or grammar errors in any locale
- English: [check]
- German: [check]
- Japanese: [check]
- Verified: [YES/NO]
- [ ] Cross-field keyword combinations produce intended search queries (iOS)
- Example: Name "Meditation" + Keyword "sleep" = searchable for "meditation sleep"
- Verified: [check each primary keyword]
- [ ] Visual asset recommendations are specific and actionable
- [Check if applicable — depends on whether visual assets were part of plan]
- [ ] Localized metadata is genuinely localized (not just translated)
- German keywords are German-specific (not English translated): [check]
- Japanese keywords are market-aware: [check]
- Verified: [YES/NO]
- [ ] No sensitive or brand-risky terms introduced
- Verified: [YES/NO]
- [ ] **No prohibited keywords** — re-scan all fields for banned terms
- iOS banned terms: [none found]
- Android banned terms: [none found]
- Verified: [YES/NO]
- [ ] **No competitor trademarks** — verify no competitor brand names leaked into any metadata field
- Verified: [YES/NO]
- [ ] **No unverifiable claims** — no superlatives without evidence
- Verified: [YES/NO]
- [ ] **No platform references** — no "Android"/"Google Play" in iOS metadata or vice versa
- iOS metadata: no Android references [YES/NO]
- Android metadata: no iOS references [YES/NO]
- [ ] **No formatting violations** — no emojis, ALL CAPS (unless brand name), or special characters in titles
- Verified: [YES/NO]
- [ ] **Accurate feature descriptions** — every claimed feature exists in the app
- "500+ guided meditations" — does the app have 500+? [check]
- "Sleep sounds" — feature exists? [check]
- All claims verified: [YES/NO]
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 · 471 lines · 0 tokens per session scan A 0d57bfafbd8c
reviewer is an agent published in the GitHub repository luongnv89/skills (123 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,775 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.
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。.
gitops
你是版本控制操作员。负责代码的同步、提交和推送，确保变更被正确记录到版本库。你不修改代码，只做版本控制操作。.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
vision
Analyze images with task-aware visual reasoning.