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 refine-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/refine-write-tech-note)<a href="https://agentmods.dev/skills/aiya000/dotfiles/refine-write-tech-note"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/refine-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/refine-write-tech-note"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/refine-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 | $0.00087 | $0.01871 |
| Opus 5.5 | $0.00035 | $0.00748 |
| Sonnet 5.5 | $0.00017 | $0.00374 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
refine-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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
refine-write-tech-note
Turn one review into durable changes to ~/.claude/skills/write-tech-note/, without letting that skill grow into a diary.
The skill being refined consists of:
SKILL.md— hard requirements, workflow, self-review checklist, notesreferences/style-guide.md— the user's voice, numbered sections (§1–§7)references/article-patterns.md— the five skeletons (型A–E)references/platforms.md— how the current directory decides Zenn vs Qiita, and every difference that follows (output path, file format, notation, title limit, per-platform self-review)references/review-log.md— one entry per review, the only place that keeps review text verbatim
Inputs
Collect these before changing anything. Ask only for what cannot be found.
- The review. From
ARGUMENTS, the user's message, or a file path. Keep the reviewer's words exactly; they go into the log verbatim. Identify the reviewer: Zenn's AI review, a human (record the role, never the name), or the user's own 推敲 (then the review isgit diffof the article since the draft commit, and every hunk is a comment). - The article. The most recent article written with
write-tech-notein this session, or the path the user names. If neither is known, list the article repositories (~/Repository/zenn-old/articles/,~/Repository/zenn-articles/,~/Repository/qiita-draft/) by modification time and ask. Read it whole, and note its pattern (A–E), register, and line count. - What happened while writing it. If the article was written in this session, list the production failures from the conversation: output that was typed before it was run, personal identifiers found in captured output, commands the permission system denied, links that had to become
TODO:, claims that did not reproduce. Reviews never see these, and they are the most reusable lessons. If the article was not written in this session, skip this and say so in the report.
Classify every point
For each praised point, each criticised point, and each production failure, decide one of:
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 Changed · +2 lines 697c2c46c102
- 1mo ago First seen · 69 lines · 87 tokens per session scan A 3658fa9f0d01
refine-write-tech-note is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,871 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
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.
rescue__pull_request_review
An automated workflow for handling GitHub pull-request review comments, applying requested code changes, committing them, and pushing them back.
submit__pull_request
An automated pull-request submission workflow. A pull request is a request for a code change to be reviewed and merged; this workflow writes its explanation, creates it, watches its automated checks, and fixes failed checks.
write__pull_request
A workflow for writing a pull request description, the explanation attached to a proposed code change for review. It analyses the changes and commit history.
monitor__ci_status
An automated monitor for GitHub Actions, the service that runs checks such as tests after code changes. It watches all checks after a pull request or a push to a pull-request branch and can invoke a failure-recovery process.
monitor__pull_request_conflict
An automated check for GitHub pull requests, which are proposed code changes awaiting review or merging.