agentmods.dev

rankings-validator

rankings-validator is an agent for Claude Code from LouisLau-art/multi-agent-skills-catalog. It costs 0 tokens per session (761 once invoked), scanned A, original, MIT.

A validation agent for ranking datasets, which are ordered lists of items with scores or popularity measures. It checks that refreshed files contain the expected data, fields, ordering, timestamps, and trends.

In plain words
What is it for?
Use it after ranking data refreshes to check dataset sizes, JSON validity, continuous ranks, required fields, sensible values, snapshot changes, API errors, and pagination.
Why use it?
It catches missing rows, malformed data, unexpected ranking changes, and signs of incomplete or rate-limited API responses.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

not rated 2repo yesterday A scan 0 tokens original MIT

Good fit Use it after ranking data refreshes to check dataset sizes, JSON validity, continuous ranks, required fields, sensible values, snapshot changes, API errors, and pagination.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/louislau-art/multi-agent-skills-catalog/rankings-validator
View source ↗ LouisLau-art/multi-agent-skills-catalog louislau-art.github.io
Install

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.

Clone the repo
git clone --depth 1 https://github.com/LouisLau-art/multi-agent-skills-catalog

Made for: Claude Code.

Wrote 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.

agentmods badge for rankings-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/louislau-art/multi-agent-skills-catalog/rankings-validator/github.svg)](https://agentmods.dev/agents/louislau-art/multi-agent-skills-catalog/rankings-validator)
Your own site
<a href="https://agentmods.dev/agents/louislau-art/multi-agent-skills-catalog/rankings-validator"><img src="https://agentmods.dev/badge/agents/louislau-art/multi-agent-skills-catalog/rankings-validator/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.

agentmods 80×15 button for rankings-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/louislau-art/multi-agent-skills-catalog/rankings-validator"><img src="https://agentmods.dev/badge/agents/louislau-art/multi-agent-skills-catalog/rankings-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00761
Opus 5.5 $0.00000 $0.00304
Sonnet 5.5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 2mo ago against content hash f7fea7c5bc4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rankings-validator 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 2mo 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.

.claude/agents/rankings-validator.md · 95 lines

What it actually says

Rankings Validator Agent

专门用于验证排名数据质量的子代理。

任务

在每次排名数据刷新后运行质量检查，验证数据完整性、趋势异常和 API 限制。

验证清单

数据完整性检查

  • docs/data/context7_docs_popular_top50.json 存在且包含 50 行
  • docs/data/context7_docs_extended_top1000.json 存在且包含 1000 行
  • docs/data/skills_sh_all_time_top2000.json 存在且包含 2000 行
  • docs/data/context7_skills_ranked_all.json 存在
  • docs/data/context7_rankings_manifest.json 存在且与数据集同步

数据质量检查

  • 排名顺序连续且没有间隙（1, 2, 3, ...）
  • 市场份额/分数值合理（非负数，在预期范围内）
  • 时间戳合理（不太远的过去，不是未来）
  • 必要字段存在（rank, title, source 等）

趋势异常检查

  • 与前一个快照相比，排名变化不超过合理阈值
  • 没有突然的大规模数据丢失或重置
  • 流行度/市场份额变化在预期范围内
  • 没有明显的 API 速率限制或截断迹象

API 限制检查

  • Context7 API 响应完整（不是截断或错误的）
  • skills.sh API 响应完整
  • 没有 HTTP 错误或速率限制头
  • 分页已正确处理（没有重复或遗漏的行）

验证脚本

项目中的验证脚本：

# 检查排名数据是否存在
ls -la docs/data/

# 检查 JSON 格式有效性
python3 -m json.tool docs/data/context7_docs_popular_top50.json > /dev/null

# 检查行数
python3 -c "import json; print(len(json.load(open('docs/data/context7_docs_popular_top50.json'))))"

输出格式

验证报告应包括：

通过

检查 状态 详情
检查名称 ✅ 通过 细节

警告

检查 状态 详情
检查名称 ⚠️ 警告 细节

失败

检查 状态 详情
检查名称 ❌ 失败 细节

恢复策略

如果验证失败：

  1. 小问题 - 记录警告并继续
  2. 数据质量问题 - 保留现有快照，不要覆盖
  3. API 失败 - 使用之前的快照直到 API 恢复
  4. 严重损坏 - 从 git 历史恢复最后已知的良好版本

Git 恢复命令

# 查看数据文件的历史
git log --oneline -- docs/data/

# 恢复最后已知的良好版本
git checkout <commit-hash> -- docs/data/
Changes

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.

  1. 2mo ago First seen · 95 lines · 0 tokens per session scan A f7fea7c5bc4b

Subscribe to this mod's changes

rankings-validator is an agent published in the GitHub repository LouisLau-art/multi-agent-skills-catalog (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 761 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 2026-08-31.

Analytics and metricsClaude Codeai-agentautomationcontext7curationdeveloper-tools
Related

rankings-validator compared with agents from other repositories

rankings-validator next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rankings-validatorLouisLau-art/multi-agent-skills-catalogAgent2yesterdayMITA0Claude Code
librarianpjt222/agent-almanacAgent43yesterdayMITA26Claude Code
playwright-test-generatormicrosoft/playwrightAgent99ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79ktodayMITA33Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
code-revieweranthropics/claude-cookbooksAgent54k3d agoMITA52Claude Code