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.
git clone --depth 1 https://github.com/runnithan/claudex-setupWrote 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/runnithan/claudex-setup/weekly-update)<a href="https://agentmods.dev/commands/runnithan/claudex-setup/weekly-update"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/weekly-update/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/commands/runnithan/claudex-setup/weekly-update"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/weekly-update.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 | $0.00075 | $0.05737 |
| Opus 5.5 | $0.00030 | $0.02295 |
| Sonnet 5.5 | $0.00015 | $0.01147 |
| Haiku 4.5 | $0.00007 | $0.00574 |
Grade A, and why
weekly-update 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 today.
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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/weekly-update: the whole weekly pass, one decision sheet
The hub's weekly routine is nine commands in a fixed order, each stopping for its own approval dialogs; by hand it took two days, and a forgotten stage leaves a gap. This command runs every stage in one session, holds every question back, and asks them all at once on one numbered sheet. Then it applies what the owner approved, ledgers every outcome, commits, and asks before anything is pushed. Each stage runs only when this checkout has what it needs (§0), so the same file works in the private hub and in the public mirror.
After any compaction, re-read this whole file (.claude/commands/weekly-update.md), the state
file, and the command file of the stage you are in. Compaction keeps only the start of a long
command.
What a finished run leaves behind
- Every transcript the scheduled job fetched, and every course video missing from disk where the
hub has a course source, committed under
transcripts/and ledgered inlessons/.processed.json. - New lessons from transcripts and from the social sources, verified, indexed, and consolidated until a pass changes nothing.
- The week's discoveries (tools, repos and uses) in
discoveries/INDEX.md, each verified or marked unconfirmed. - Both changelog ledgers advanced to the newest release, with every entry triaged.
- Every vendored skill compared with its upstream, and any new upstream commit on the sheet with its diff already read.
- Every tracked area's
current.mdrefreshed (design and non-codebase snapshots carried forward and labelled as such), its window reconciled from one shared trace saved asprojects/top-tips-trace-<date>.md, and its audit-log row andlast_auditupdated. - One decision sheet answered, with every outcome ledgered where its source command ledgers it. Nothing is applied without a yes, and nothing declined is offered again.
python3 scripts/validate-artifacts.pypassing, the publish dry run clean on the final HEAD where the hub hasscripts/publish.sh, the hub committed, and the push question asked.- A report with exact counts per stage.
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.
- today Changed · +2 lines fc76fe2d6e22
- yesterday First seen · 371 lines · 75 tokens per session scan A 7bfa2a01f7e9
weekly-update is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 5,737 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 2026-10-20.
Other commands, from other repositories
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-export
Export instincts for sharing with teammates or other projects.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.