weekly

weekly is a skill for Claude Code, Codex from jzhao234/big-brain. It costs 73 tokens per session (731 once invoked), scanned A, original, MIT.

A guided weekly review command for the big-brain second-brain vault, which is a personal system for notes, projects, and tasks. It reviews the inbox, active projects, overdue work, and vault health.

In plain words
What is it for?
Use it with /weekly to triage inbox items, review projects, reschedule or drop overdue tasks, check the vault, and write a review summary.
Why use it?
It helps turn accumulated notes and unfinished work into an up-to-date list of projects, tasks, blockers, and decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with /weekly to triage inbox items, review projects, reschedule or drop overdue tasks, check the vault, and write a review summary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jzhao234/big-brain/weekly
Install

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.

Any agent
npx skills add jzhao234/big-brain --skill weekly
Clone the repo
git clone --depth 1 https://github.com/jzhao234/big-brain

Made for: Claude Code, Codex.

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 weekly

README.md
[![agentmods](https://agentmods.dev/badge/skills/jzhao234/big-brain/weekly.svg)](https://agentmods.dev/skills/jzhao234/big-brain/weekly)
Your own site
<a href="https://agentmods.dev/skills/jzhao234/big-brain/weekly"><img src="https://agentmods.dev/badge/skills/jzhao234/big-brain/weekly.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 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 $0.00073 $0.00731
Opus 5 $0.00036 $0.00365
Sonnet 5 $0.00015 $0.00146
Haiku 4.5 $0.00007 $0.00073

Measured 6d ago against content hash e9ea68385ddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 6d 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.

skills/weekly/SKILL.md · 27 lines

How it starts

The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.

weekly

A guided review of the big-brain vault (whichever big-brain resolves — BIG_BRAIN_VAULT, --vault, or nearest brain.config.json). Work through it with the user — propose, confirm, act. The outcome: an empty inbox, honest project statuses, a task list that reflects reality, and a written record.

Order of operations

  1. Snapshot. big-brain status + big-brain doctor. Lead with the two or three things that most need attention (overdue tasks, stale projects, inbox pileup, broken links).
  2. Inbox triage. For each note in the inbox, propose exactly one destination: merge into an existing note/project, become a new linked note, become tasks, or archive. Batch the proposals, get one confirmation, execute, archive the processed captures.
  3. Project walk. For each active project: last Log entries, open tasks, blockers. Ask the one question that matters: is this still active? Update statuses (big-brain project status <ref> paused|done|dropped) — a shorter honest list beats an impressive stale one. For projects untouched for 2+ weeks, suggest a concrete next task or a status change.
  4. Task hygiene. Overdue tasks get one of: do-this-week (new due date), someday (drop the date), or dead (remove). Never let a due date silently roll forward twice — that's a signal the task is mis-scoped or unwanted; say so.
  5. Doctor fixes. Fix broken wikilinks and duplicate names found in step 1 where the fix is obvious; list the rest.
  6. Consolidate. The doctor's bloated-note and possible-duplicate findings are the queue; big-brain related <note> shows what a note overlaps with. Propose (never apply unconfirmed): split a bloated note's grown sections into linked notes; merge near-duplicates into one canonical note (archive the loser, keep its title as an alias); prune stale facts — while reading project notes in step 3, flag statements that no longer hold (old statuses, superseded decisions, dead links to reality) and update or strike them. One batch of proposals, user confirms, execute. Memory that never gets consolidated rots; this step is why the vault stays trustworthy.
  7. Write the record. Append a short summary to today's daily note Log: projects reviewed, status changes, inbox items processed, consolidations made, what the user said matters next week. If the vault has git auto-commit enabled, the review's edits commit and push on their own; otherwise commit at the end (git -C <vault> add -A && git commit -m "weekly review <date>" && git push).

Read the full file on GitHub · 27 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. 6d ago First seen · 27 lines · 73 tokens per session scan A e9ea68385ddd

Subscribe to this mod's changes

weekly is a skill published in the GitHub repository jzhao234/big-brain (0 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 731 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

priority-dashboard

Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.

vincentmumme/personalos-boilerplate · 60 tokens

wrap-session-up

End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.

michaeljauk/brain-starter · 60 tokens

task-manager

Use this when {{username}} or an agent wants to add, review, prioritize, complete, defer, park, or inspect todos, open loops, confirmed actions, waiting states, or attention triggers. Maintains atomic records under operations/actions/ and operations/attention-triggers/ as the only local action truth. Do NOT use for…

vincentmumme/personalos-boilerplate · 90 tokens

gws-obsidian-prep

Cross-skill recipe: fetch today's (or tomorrow's) Google Calendar events via gws CLI and create meeting prep notes in the Obsidian vault.

michaeljauk/brain-starter · 0 tokens

resume

A workflow for reopening a paused task by scanning its saved project notes, blockers, logs, and delegated work. It presents the parked tasks so the user can choose which one to continue.

dzhokhov/markdown-agent-vault-ru · 204 tokens

vault-onboarding-guide

An interactive guide for learning a file-based knowledge store with an agent. It teaches how to organize incoming material, projects, plans, tasks, logs, parked work, and resumed work.

dzhokhov/markdown-agent-vault-ru · 187 tokens