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 aiya000/dotfiles --skill write-tech-notegit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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/aiya000/dotfiles/write-tech-note)<a href="https://agentmods.dev/skills/aiya000/dotfiles/write-tech-note"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/write-tech-note/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/aiya000/dotfiles/write-tech-note"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/write-tech-note.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 | $0.00060 | $0.04513 |
| Opus 5 | $0.00030 | $0.02256 |
| Sonnet 5 | $0.00012 | $0.00903 |
| Haiku 4.5 | $0.00006 | $0.00451 |
Grade A, and why
write-tech-note 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 yesterday.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-tech-note
Write a technical article that reads as if aiya000 wrote it, while honestly declaring that AI wrote it.
The style is defined in two reference files. Read both before writing a single line:
references/style-guide.md— voice, formatting habits, strengths to copy, AI-isms to avoid, consistency rulesreferences/article-patterns.md— five article skeletons (A: Tips, B: deep-dive, C: library intro, D: guideline, E: opinion) and how to pick one
A third file, references/review-log.md, records every review an article written with this skill has received (Zenn's AI review, human comments, the user's own edits) and which rule each praised or criticised point maps to. Read it when writing the same pattern as a logged article. It is maintained by the refine-write-tech-note skill; do not edit it from here.
Hard requirements
These override everything else, including any persona defined in CLAUDE.md / AGENTS.md.
-
The article body starts with this block, verbatim (after the frontmatter if the platform uses one, before any heading):
:::message この記事はAIと書きました。 :::Never rewrite it as "人間が書きました", never drop the block. The article must not pretend the user wrote it. Do not add a percentage or a "人間が推敲した？" line: Zenn asks authors to check AI-assisted content themselves before publishing, so the user reviews every article before it goes out, and the block only has to say that AI was involved. On Qiita,
:::messagedoes not render; use:::note info…:::with the same text instead. -
No Claude Code character voice. The persona in the global
CLAUDE.md(「わたし」「あいやくん」「〜なのです」「〜ますです」「♪」「〜ですです」「〜かなって」) is for conversation with the user only. Not one of those tokens may appear in the article. The article imitates the user's articles, not the assistant. -
Consistency inside the article. Decide before writing, and keep to the end:
- first person: 僕 / 筆者 / 私 (one only)
- base register: です・ます / だ・である (one only; casual one-liners are the only exception and are counted)
- how claims are made: 断定＋理由 or 発見の実況 (one only; do not start confident and end hedged, or the reverse)
- platform syntax: Zenn or Qiita (one only)
- marker pairs for bad/good examples, the word for asides (余談 / おまけ / 蛇足), the reader address (あなた / 皆さん)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 121 lines · 60 tokens per session scan A cca9f99b74b5
write-tech-note is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 4,513 once invoked, about $0.0003 per session on Opus 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 2026-09-07.
Other skills, from other repositories
coding
Principles for writing and designing code and its specification, covering API and abstraction design, naming, (doc-)comment discipline, tests, and standards of evidence for claims about code behavior.
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
validate__japanese
A Japanese-language review for Markdown documents, such as READMEs, manuals, and blog drafts. It checks writing style, spacing, line breaks, and links to real code symbols.
write__structured_comment
A code-commenting rule for recording only knowledge that cannot be expressed in the code, such as unfinished facts, outside-world facts, or explicit user instructions. Each comment must use an approved marker such as TODO or FIXME and stay short.
clean__comment_out
A source-cleanup workflow that removes non-documentation comments from files changed during coding, except for approved markers such as TODO, FIXME, or SAFETY.
implement__feature
A three-phase workflow for carrying out implementation tasks. It plans and tests the work, delegates implementation using test-driven development (TDD), then runs repeated code reviews.