wiki-bot: Skill for Claude Code

.agents/skills/nekoquote-incremental/SKILL.md

nekoquote-incremental is a skill for Claude Code, Codex from re0wiki/wiki-bot. It costs 38 tokens per session (3,504 once invoked), scanned A, original, MIT.

A runbook for incrementally importing NekoQuote messages from Discord exports, translating them, building monthly tables, and deploying the results. A runbook is a documented procedure for repeating a task and handling failures.

In plain words
What is it for?
It is for maintaining the NekoQuote quote database, processing exported Discord messages, translating new entries, and publishing monthly updates.
Why use it?
It gives maintainers a repeatable process for adding new quotes and recovering from unreliable collection channels. It also describes checks for duplicate imports and incomplete runs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is re0wiki/wiki-bot's own configuration. It tells Claude Code and Codex how to work on wiki-bot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wiki-bot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to re0wiki/wiki-bot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/re0wiki/wiki-bot/main/.agents/skills/nekoquote-incremental/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/re0wiki/wiki-bot

Made for: Claude Code, Codex.

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 nekoquote-incremental

README.md
[![agentmods](https://agentmods.dev/badge/skills/re0wiki/wiki-bot/nekoquote-incremental/github.svg)](https://agentmods.dev/skills/re0wiki/wiki-bot/nekoquote-incremental)
Your own site
<a href="https://agentmods.dev/skills/re0wiki/wiki-bot/nekoquote-incremental"><img src="https://agentmods.dev/badge/skills/re0wiki/wiki-bot/nekoquote-incremental/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 nekoquote-incremental

Your own site · 80×15
<a href="https://agentmods.dev/skills/re0wiki/wiki-bot/nekoquote-incremental"><img src="https://agentmods.dev/badge/skills/re0wiki/wiki-bot/nekoquote-incremental.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,504 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 $0.00038 $0.03504
Opus 5.5 $0.00015 $0.01402
Sonnet 5.5 $0.00008 $0.00701
Haiku 4.5 $0.00004 $0.00350

Measured 3d ago against content hash 83c2e0757bb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nekoquote-incremental 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 3d 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.

.agents/skills/nekoquote-incremental/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NekoQuote 增量收录 Runbook

主通道:循环任务 nekoquote(src/scripts/re0_nekoquote.py)全自动同步——FxTwitter v2 拉取长月原创(含 Note Tweet 长文,RT 剥除),复用 src/nekoquote/ 包的采集器与管线,随 main.py 循环执行、无需人工或 Discord token。.cache/nekoquote/sync_state.json 记录 source 与 last_original_id,全链成功才推进;FBK 旧 last_id 状态首次迁移时回扫至 2026-08-18,补收其漏转内容。以下手动导出流程保留为备份/排障手段(EN 与中文频道同为 FBK 转发,不互为独立兜底;FBK/nitter 是共同单点)。

长月新推的手动备份流程(2026-08-15 定稿)走英文社区 Discord 转发频道的定期手动导出 + 一键管线。直连采集与备用来源见下节;wayback CDX 被动滞后,只作补漏。

直连采集与备用来源

  • FxTwitter API v2(自动主通道)(文档、OpenAPI):无密钥,采集器为 src/nekoquote/fxtwitter.py。时间线混有转推、同页时间序不严格且可能重复,按 id 去重、按 author.screen_name / reposted_by 过滤;count=100 实测仍每页 20,必须按 cursor.bottom 翻页。每轮从最新页扫到上次全链成功的 last_original_id 所在页,处理完该页后停止;FBK 旧状态首轮改用 stop_before=2026-08-18,全新 wiki 基线以全时间线数值最大的原创 id 播种、不收录存量(当次实测 164 页)。since 只对不带游标的请求生效,后续游标页会回到未过滤时间线,生产不依赖它;无界扫描遇 204/空页正常结束,有界扫描若 204、空页或游标耗尽仍未抵达边界则非零且不推进,游标重复、HTTP/API 错误同样非零。长文 is_note_tweet=true 时 text 仍含完整全文;公共实例无 SLA。2026-10-26 隔离数据真实干跑:首轮 90 页补出 3 篇长文,第二轮 5 页命中边界且零新增。/2/search 当次 from: 查询返回 404,不用于发现。
  • teapaw HTML(https://teapaw.org/nezumiironyanko?filter=posts):首页 20 条原创即含 10-12 两篇与 10-18 一篇长文;.timeline-item 可关联状态 id,.tweet-content 含长文全文与结尾,可作免费补漏/对账来源。RSS 与 HTML 覆盖不同,当次 RSS(含 ?filter=posts 变体)不含这三条,不能以 RSS 覆盖推断原创停更。HTML 不是稳定接口,结构变化须响亮失败。
  • X 官方 API(用户时间线、定价):文档支持 since_id、游标分页、排除转推及长文全文字段;现行按量付费无订阅,Posts Read 为 $0.005/返回条数。需开发者账号与 credits,本仓库尚未做凭据实测。
  • ReZeroDB 作者推存档(入口):作品向筛选友好,但页面自述每三个月更新,只宜低频对账/补漏,不宜承担及时同步。

上游:EN Discord 转发频道

频道经 nitter 持续追 nezumiironyanko(另有 Rezero_official 等)。三个转发账号:

  • Tappei Nagatsuki——长月专线 webhook(旧式 content 格式,尾部带 [Link](url) 行)
  • FBK——混合 bot(Discord 新版组件布局,content/embeds 全空,正文在组件树里;附机翻段)
  • Re:Zero Official——官推(不收)

Read the full file on GitHub · 75 lines

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. 3d ago Changed · +1 lines 83c2e0757bb4
  2. 9d ago Changed · +17 lines 11883dd1ab45
  3. 1mo ago Changed · -3 lines a415b992cb89
  4. 1mo ago First seen · 60 lines · 38 tokens per session scan A c0ea04297c6f

Subscribe to this mod's changes

nekoquote-incremental is a skill published in the GitHub repository re0wiki/wiki-bot (5 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 3,504 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-22.

Related

nekoquote-incremental compared with skills from other repositories

nekoquote-incremental next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nekoquote-incrementalre0wiki/wiki-botSkill53d agoMITA38Claude Code, Codex
schema-explorationlangchain-ai/deepagentsSkill31kyesterdayMITA57Claude Code, Codex
matlabK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA44Claude Code
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
mempalace-recallMemPalace/mempalaceSkill60kyesterdayMITA94Claude Code
analyze-marketlangchain-ai/deepagentsSkill31kyesterdayMITA34Claude Code, Codex
haikuagno-agi/agnoSkill43kyesterdayApache-2.0A0Claude Code, Codex