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 agentmods add commands/xbluesky/vatt-ghern/weeklygit clone --depth 1 https://github.com/XBlueSky/vatt-ghernWrote 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/commands/xbluesky/vatt-ghern/weekly)<a href="https://agentmods.dev/commands/xbluesky/vatt-ghern/weekly"><img src="https://agentmods.dev/badge/commands/xbluesky/vatt-ghern/weekly.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00315 |
| Opus 5 | $0.00013 | $0.00158 |
| Sonnet 5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
weekly 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.
What it actually says
Execute the daily-news skill in weekly rollup mode for the vatt-ghern blog.
Use the daily-news skill in this plugin to:
- Skip Step 2 (fetch sources), Step 3 (score/filter), Step 4 (pick), Step 5 (deep-story selection), Step 6 (roundup).
- Run
node ${CLAUDE_PLUGIN_ROOT}/skills/daily-news/scripts/load-past-roundups.mjs --days=7to gather past 7 days' sidecars. - Read the archetype reference at
skills/daily-news/references/archetypes/weekly-rollup.md. - Author exactly ONE
src/posts/YYYY/MM/DD/weekly.html(where YYYY-MM-DD is today, a Monday) + matching.11tydata.json. - Run validation (
archetype-check,html-validate,link-check). Anti-dedup gate is bypassed by theoverride_dup_check: trueflag in the sidecar. - Open a PR titled
weekly: <week range> rollupagainstmain.
Do not merge — the PR waits for human review and Cloudflare Pages preview.
If the past 7 days had fewer than 3 roundups, skip the rollup and report that to the user. No PR.
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.
- 5d ago First seen · 27 lines · 25 tokens per session scan A 7477dbcb570d
weekly is a command published in the GitHub repository XBlueSky/vatt-ghern (5 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 315 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
build
Command "build" from wechatsync/Wechatsync, covering build project and 执行步骤.
scan
Recover files that a crashed session left converted to UTF-8.
cf-refresh
Capture a fresh Cloudflare snapshot, regenerate the report + beta advisor, and rebuild the dashboard data.
ai-update
Update all CLAUDE.md files across the monorepo to reflect the current state of the codebase.
velog
Velog MCP 툴을 사용해서 아래 요청을 처리해줘.
pr
Create a Pull Request from the current branch to boostcampwm-2024:develop.