M3E: Skill for Claude Code

.claude/skills/daily-sync/SKILL.md

daily-sync is a skill for Claude Code from akaghef/M3E. It costs 147 tokens per session (992 once invoked), scanned A, original, MIT.

A scheduled workflow for moving development work from a `dev-beta` Git branch to a `final` directory. It commits and pushes tracked changes, runs a build and bounded tests for final changes, and only commits the final update when those checks pass.

In plain words
What is it for?
It is for unattended daily synchronization, pushing pending beta work, updating final files, and validating final changes before they are pushed.
Why use it?
It removes repetitive manual branch synchronization while stopping on divergent history, failed checks, or untracked files. It also keeps failed final updates from being committed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is akaghef/M3E's own configuration. It tells Claude Code how to work on M3E 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 M3E configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/nisimoriyuuya/dev/M3E/scripts/ops/daily-sync.sh.

View source ↗ akaghef/M3E
Reuse

Borrowing it

Nothing to install: this file belongs to akaghef/M3E. 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/akaghef/M3E/main/.claude/skills/daily-sync/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/akaghef/M3E

Made for: Claude Code.

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 daily-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/akaghef/m3e/daily-sync/github.svg)](https://agentmods.dev/skills/akaghef/m3e/daily-sync)
Your own site
<a href="https://agentmods.dev/skills/akaghef/m3e/daily-sync"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/daily-sync/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 daily-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/akaghef/m3e/daily-sync"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/daily-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 992 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 $0.00147 $0.00992
Opus 5.5 $0.00059 $0.00397
Sonnet 5.5 $0.00029 $0.00198
Haiku 4.5 $0.00015 $0.00099

Measured 5d ago against content hash e94839e2bea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

daily-sync 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 5d 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.

.claude/skills/daily-sync/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

daily-sync — dev-beta 日次同期

scripts/ops/daily-sync.sh を実行するだけの薄いスキル。

実行

/Users/nisimoriyuuya/dev/M3E/scripts/ops/daily-sync.sh

確認だけなら:

/Users/nisimoriyuuya/dev/M3E/scripts/ops/daily-sync.sh --dry-run

final/ 同期を省く場合:

/Users/nisimoriyuuya/dev/M3E/scripts/ops/daily-sync.sh --no-final

ルーチン

  1. dev-beta に移動し、origin/dev-beta を --ff-only で取り込む
  2. tracked change だけを git add -u で stage し、必要なら日次 commit
  3. dev-beta を push
  4. scripts/final/sync-beta-to-final.sh で beta/ → final/ を同期
  5. final/ が変わった場合だけ install / build / bounded test を実行
  6. gate が通った場合だけ final/ 更新を commit して push

安全保証

  • pull は fast-forward only。divergence は自動 merge せず停止する
  • untracked file は commit しない。secret 混入を避けるため git add -A は使わない
  • dev-beta の pending work は final gate より前に commit/push される
  • final build/test が fail または timeout した場合、final/ は commit しない
  • script 先頭で /opt/homebrew/bin を PATH 優先し、arm64 Node を使う

やらないこと

main merge、tag、GitHub Release、VM test、人間 gate は実行しない。 それらが必要な正式リリースは launch-final を使う。

Scheduling

スキルと script は scheduler-agnostic。登録はユーザーが選ぶ。

crontab 例:

17 5 * * * /Users/nisimoriyuuya/dev/M3E/scripts/ops/daily-sync.sh >> /Users/nisimoriyuuya/dev/M3E/logs/daily-sync.log 2>&1

LaunchAgent plist 例の保存先:

~/Library/LaunchAgents/com.m3e.daily-sync.plist

plist 例:

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"
  "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.m3e.daily-sync</string>
  <key>ProgramArguments</key>
  <array>
    <string>/Users/nisimoriyuuya/dev/M3E/scripts/ops/daily-sync.sh</string>
  </array>
  <key>StartCalendarInterval</key>
  <dict>
    <key>Hour</key>
    <integer>5</integer>
    <key>Minute</key>
    <integer>17</integer>
  </dict>
  <key>StandardOutPath</key>
  <string>/Users/nisimoriyuuya/dev/M3E/logs/daily-sync.log</string>
  <key>StandardErrorPath</key>
  <string>/Users/nisimoriyuuya/dev/M3E/logs/daily-sync.err.log</string>
  <key>WorkingDirectory</key>
  <string>/Users/nisimoriyuuya/dev/M3E</string>
</dict>
</plist>

Read the full file on GitHub · 103 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. 5d ago First seen · 103 lines · 147 tokens per session scan A e94839e2bea4

Subscribe to this mod's changes

daily-sync is a skill published in the GitHub repository akaghef/M3E (11 stars, last pushed 5d ago), licensed MIT. It adds 147 tokens to every session and 992 once invoked, about $0.0006 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 2026-10-02.