weekly-review

weekly-review is a command for Claude Code from etrebels/claude-code-growth-os. It costs 17 tokens per session (1,026 once invoked), scanned A, original, MIT.

A weekly review command for examining the past week's work and choosing one priority for the next week. It reads daily logs, feedback, customer information, and sales or account activity.

In plain words
What is it for?
Use it to summarize the week's progress, clear open marketing actions, check upcoming renewals, flag at-risk accounts, find adoption stalls, and identify expansion candidates.
Why use it?
It brings stalled work, unaddressed feedback, renewal risks, adoption problems, and growth opportunities into one review instead of leaving them scattered across records.

Command for Claude Code

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.

agentmods
npx agentmods add commands/etrebels/claude-code-growth-os/weekly-review
Clone the repo
git clone --depth 1 https://github.com/etrebels/claude-code-growth-os

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 weekly-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/weekly-review.svg)](https://agentmods.dev/commands/etrebels/claude-code-growth-os/weekly-review)
Your own site
<a href="https://agentmods.dev/commands/etrebels/claude-code-growth-os/weekly-review"><img src="https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/weekly-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.01026
Opus 5 $0.00009 $0.00513
Sonnet 5 $0.00003 $0.00205
Haiku 4.5 $0.00002 $0.00103

Measured 5d ago against content hash 8ba84aba621d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

weekly-review 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/commands/weekly-review.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly Review

Generic chassis variant. If a private operating repo (e.g. your own growth-os) defines a command with this name, that version is canonical for that repo's data.

Run an honest weekly review across the whole motion — both sides of the bowtie.

Left side (demand → close):

  1. Read the last seven entries in ops/daily-log.md.
  2. Summarize the week: what shipped, what stalled, any pattern worth naming. Read each channel or effort by the quality of relationships it surfaced, not only headline volume — one deep, high-fit relationship can be the whole return on an effort that looks thin by the numbers.
  3. Clear the loop: surface any open MARKETING-ACTION lines in ops/feedback-log.md that haven't been acted on.

Right side (post-sale — read ops/customers.md):

  1. Renewals due in the next 30 / 60 / 90 days. Flag any inside 60 days — that's when the renewal motion starts (not day 85).
  2. Accounts at risk. List anything at 🔴/🟡 — usage down, champion quiet, single-threaded — and the next step for each.
  3. Adoption stalls. Accounts stuck between onboarding and live (a workflow never turned on, a setup step blocking them).
  4. Expansion candidates. Healthy accounts ready to grow — hand to sales with the CS context.
  5. Top roadmap signals. The highest-priority items in ops/roadmap-signals.md — what product should hear, and anything shipped that still needs its buyer-facing line.

Then:

  1. Ownership read. For each live area on both sides, check it has an owner who treats the number as theirs — not just what moved this week. An area no one owns is the pattern to fix first.
  2. Chokepoint read (ops/chokepoints.md). Walk the short list of narrow dependencies most of the revenue flows through. Two questions: has anything changed hands or become more concentrated this week, and does every row still have a named owner? A row carried unresolved for 3+ reviews is re-rated, not dropped — sitting there longer earns more attention, not less. Use the same list as a news filter: market noise touching nothing on it gets no time in this review.
  3. Pick next week's single most important priority and write it to the top of ops/priorities.md.
  4. Name one thing to stop doing — and write the sentence that makes it a prune. Removal is fast and visible while building is slow and invisible, so teams drift toward cutting and call it discipline. Before anything comes off: "this is cut so that X specifically improves, measured by Y, checked on <date>." No sentence, no cut. Log the check date and read it when it arrives — an unverified cut is a dismantling, not a prune.

Lead with the summary. Don't pad it. If ops/customers.md or ops/roadmap-signals.md is empty, say so and skip that section. Reconcile the pipeline mirror against the CRM per .claude/rules/crm-usage.md — read-only beyond what the daily rituals already persisted.

Read the full file on GitHub · 43 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 · 43 lines · 17 tokens per session scan A 8ba84aba621d

Subscribe to this mod's changes

weekly-review is a command published in the GitHub repository etrebels/claude-code-growth-os (20 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 1,026 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 2026-08-30.