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 skills add Bilal140202/the-lord-of-the-skills --skill canonical_git clone --depth 1 https://github.com/Bilal140202/the-lord-of-the-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/skills/bilal140202/the-lord-of-the-skills/canonical_)<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/canonical_"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/canonical_/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.
<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/canonical_"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/canonical_.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00090 | $0.01760 |
| Opus 5.5 | $0.00036 | $0.00704 |
| Sonnet 5.5 | $0.00018 | $0.00352 |
| Haiku 4.5 | $0.00009 | $0.00176 |
Grade A, and why
acr-submission 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
投稿前 preflight（acr-submission）
触发时机
- 正文、度量、识别、机制都定了，准备投稿
- 需要一份"投出去前最后核对"的清单
关键事实（详见 resources/journal-profile.md）
- 主管/主办：财政部主管、中国会计学会主办；月刊；ISSN 1003-2886；CN 11-1078/F
- 投稿方式：仅线上投稿——经中国会计学会网站在线投稿系统（入口：www.asc.net.cn《会计研究》投稿指南页）；不接收电子邮件、纸质邮寄
- 摘要 200–300 字；关键词 3–8 个
- 注释体例：当页下注（脚注），序号用「①，②……」标识，每页单独排序
- 参考文献：著者—出版年制；文末参考文献表先中文后外文，中文按姓名拼音首字母、英文按作者姓名首字母排列
- 篇幅：全文一般不得低于 16000 字（doc/pdf/wps）；上限有"约 22000 字"之说，以官网最新指南为准
- 审稿：三审终审制 + 双向匿名审稿制；审稿周期约三个月
体例与字数以官网**最新《投稿指南》**为准。规则会变，投前务必复核，不要凭记忆。
体例 checklist
- 注释统一为当页下注（脚注），每页序号「①②……」单独排序，非尾注、非文中夹注
- 参考文献用著者—出版年制，文末表先中文后外文，排序符合规则
- 正文引用与文末参考文献一一对应、可核查；直接引用标页码
- 中文摘要 200–300 字；关键词 3–8 个；按系统要求附英文标题/摘要/关键词
- 全文字数 ≥ 16000 字（以最新指南为准）；文档为 doc/pdf/wps
- 图表规范、编号连续、有出处；变量定义表齐全
- 基金项目、作者信息按系统要求填写（正文匿名）
双向匿名 hygiene
- 上载文档（初稿、修改稿、修改说明）中去除可识别作者身份的信息
- 自引改为第三人称或匿名占位
- 文件属性（作者名、单位）已清除
- 致谢、基金号等敏感信息按匿名要求处理
提交前内容复核（调用其它 skill）
- 落点是会计议题而非金融机理（
acr-fit-positioning） - 会计度量构造透明可复现（
acr-measurement） - 制度/准则背景准确、时点无误（
acr-institutional-standards） - 识别策略立得住（
acr-identification） - 机制落到信息渠道（
acr-mechanism） - 贡献兼顾理论与准则/监管实务（
acr-implications）
反模式
- 凭记忆套体例，不查最新《投稿指南》
- 用尾注/文中夹注替代当页下注，或用编号 [1][2] 制替代著者—出版年制
- 想走邮箱投稿（本刊仅线上）
- 忘清匿名信息就投双盲
投稿前体例审稿期待（决策表）
《会计研究》由中国会计学会主办，是 CSSCI 唯一权威顶级会计学期刊，初审常因体例与匿名问题直接退回，与稿件质量无关。下表把易错点与退稿模式对齐（具体数值一律以官网最新《投稿指南》为准）：
| 审查点 | 达标线（以最新指南为准） | 常见退稿/退修模式 |
|---|---|---|
| 注释体例 | 当页下注（脚注），每页「①②」单独排序 | 用尾注或文中夹注 [1][2] |
| 参考文献 | 著者—出版年制，文末先中文后外文 | 用顺序编码制 [1][2] |
| 摘要/关键词 | 摘要 200–300 字、关键词 3–8 个 | 摘要过短或关键词超限 |
| 篇幅 | 全文一般不低于 16000 字 | 不足字数下限 |
| 匿名 | 去除作者身份、清文件属性、自引第三人称化 | 正文/文件属性泄露身份 |
| 投稿渠道 | 仅线上（中国会计学会网站系统） | 走邮箱或纸质邮寄 |
微型走查：投前自检（数字示意）
虚构稿《关键审计事项披露与分析师预测准确性》准备投稿，自检（示意）：正文 18200 字（≥16000 达标）、中文摘要 248 字（200–300 达标）、关键词 5 个（3–8 达标）、注释为当页下注每页单独排序、参考文献著者—出版年制且中文在前。匿名核查发现一处自引写作"我们之前的研究（作者，2021）"——改为第三人称占位"已有研究（XXX，2021）"；文件属性中作者单位未清，已清除。结论：体例与匿名达标，可投。
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.
- 1mo ago First seen · 97 lines · 90 tokens per session scan A 83b91c73b792
acr-submission is a skill published in the GitHub repository Bilal140202/the-lord-of-the-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,760 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
serpsmith
Publish SEO articles, verify unattended health, and gate source-to-runtime releases.
tool-calling-tutor
Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.
ainb-fleet:daemons
Runtime-health view of the four fleet daemons — phone bridge, notifyd, ATC, and the fleet auto-continue daemon — in one table. Each row reports state (running / stopped / unknown), pid, uptime, last activity, error count, and a HEALTH reason that distinguishes a clean stop from a crash (stale heartbeat) or a…
ainb-fleet:atc
ATC (Air Traffic Control) — the single operator-visible fleet supervisor, in exactly one mode: lite (no LLM: deterministic scan, known-transient retry policy, safety caps, evidence) or full (the persistent orchestrating brain). Full mode is a plain ainb session (Claude or Codex) running a generated policy, woken on a…
ainb-fleet:fleet-needs
Workflow-backed Jarvis control panel. Runs the deterministic hangar workflow with verb=needs (discover → enrich → prioritize), renders the Jarvis HUD from its render-ready cards, fires AskUserQuestion per blocked session, and routes each answer back via tmux send-keys (broker fallback only). Requires the workflow gate…
first-plan-lens-mobile
Stack lens para mobile - React Native, Swift (iOS), Kotlin (Android), Flutter. Use durante Discovery quando pubspec.yaml, Package.swift, build.gradle.kts (Android) ou react-native em deps for detectado. Cobre navegação, estado, módulos nativos, build/distribuição.