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 ANcpLua/ancplua-claude-plugins --skill tomevault-publishgit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/tomevault-publish)<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/tomevault-publish"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/tomevault-publish/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/ancplua/ancplua-claude-plugins/tomevault-publish"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/tomevault-publish.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 | $0.00097 | $0.02777 |
| Opus 5.5 | $0.00039 | $0.01111 |
| Sonnet 5.5 | $0.00019 | $0.00555 |
| Haiku 4.5 | $0.00010 | $0.00278 |
Grade A, and why
tomevault-publish 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tomevault-publish
Everything needed to take an instruction file from a repo to a published, high-grade TomeVault Tome — distilled so you never re-read the docs. Two halves: the model (what Skills, Tomes, and configs are) and the workflow (CLI, Studio publish, grading rubric).
1. The model
Instruction files
An "instruction file" is any Markdown file beside your code that tells an AI tool something true. Two loading patterns:
- Always-on config — loads every turn.
AGENTS.md(repo root, cross-tool) is the 2026 default;CLAUDE.md(Claude-only),.cursorrules,.windsurfrules, and.github/copilot-instructions.mdare tool-specific equivalents. Keep it terse — it costs context on every task. Read by Claude Code and other agent CLIs. - On-demand skill —
SKILL.mdloads only when a task matches its description. It costs nothing until it triggers.
The test for "config vs skill": does this apply to almost every task in the repo? Yes means AGENTS.md; only sometimes means a Skill.
Skill
A folder plus a SKILL.md with two parts:
- Header (frontmatter
description) — under 1024 characters, imperative, intent-focused. The description is the trigger. Write the body in the same voice — direct, imperative lines, which agents follow more reliably than soft suggestions. - Body — under 500 lines or 5000 tokens. Steps, gotchas, examples. Bulk goes into a
references/folder, loaded on demand.
Write a Skill when you would otherwise explain the same procedure more than twice. Universal rules belong in AGENTS.md, not a Skill.
AGENTS.md vs SKILL.md
| Aspect | AGENTS.md | SKILL.md |
|---|---|---|
| Loads | Every conversation, always on | Only when the task matches its description |
| For | Truths about the whole project | One specific procedure |
| Lives | One file at repo root | A folder with SKILL.md plus optional files |
| Context cost | Every task | Nothing until it triggers |
| Trigger | Its existence | The description field |
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 · 150 lines · 97 tokens per session scan A 0a5cabc58c6e
tomevault-publish is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 2,777 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 2026-10-01.
tomevault-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tomevault-publishANcpLua/ancplua-claude-plugins | Skill | 6 | 2d ago | MIT | A | 97 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 316k | 7d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |