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 skills add sdaluga/claude-cowork-playbook --skill weekly-account-reviewgit clone --depth 1 https://github.com/sdaluga/claude-cowork-playbookWrote 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/skills/sdaluga/claude-cowork-playbook/weekly-account-review)<a href="https://agentmods.dev/skills/sdaluga/claude-cowork-playbook/weekly-account-review"><img src="https://agentmods.dev/badge/skills/sdaluga/claude-cowork-playbook/weekly-account-review/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/skills/sdaluga/claude-cowork-playbook/weekly-account-review"><img src="https://agentmods.dev/badge/skills/sdaluga/claude-cowork-playbook/weekly-account-review.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 | $0.00071 | $0.01059 |
| Opus 5 | $0.00036 | $0.00530 |
| Sonnet 5 | $0.00014 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
weekly-account-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Account Review
Produce one prioritised list of what to do this week across a portfolio, with the reasoning visible so the user can disagree with a specific line rather than the whole thing.
This skill is built to run unattended as a scheduled task. That means: never ask a clarifying question. Make the most reasonable interpretation, state the assumption at the top of the output, and proceed.
Inputs
Expect a portfolio folder with one subfolder per account. If the structure is different, adapt — Glob first, describe what you found, and work with it.
Look for, in each account:
- Call notes and meeting summaries (most recent first)
- Email threads or exports
- Pipeline or CRM extracts
- Anything with a date in the filename
Method
Work through this in order. Do not skip to the list.
1. Build the clock. For each account, find the date of the most recent genuine customer interaction — not an internal note, not an automated notification. Rank the portfolio by that date, oldest first. Silence is the single most reliable signal in account work and the easiest one to miss.
2. Find the open loops. Search the material for commitments that were made and not visibly closed: "I'll send", "we'll get back to you", "let me check with", "by end of week". Each unclosed loop is an action, and it belongs to whoever made the commitment.
3. Find the changes. For the top accounts by value, run one web search each for news in the last 30 days — leadership changes, earnings, acquisitions, layoffs, a new strategic initiative. Cite anything you use. Skip this step entirely if web access is unavailable; say so rather than guessing.
4. Score, then sort. Rank every candidate action on:
- Reversibility — will waiting a week make this materially harder to fix?
- Value at stake — the deal or renewal amount actually exposed.
- Effort — a 20-minute email outranks a two-day workshop at equal value.
An action that is urgent, high-value, and cheap goes first. Say so explicitly when something scores high on all three; that is the one thing the user must not miss.
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.
- 12d ago First seen · 73 lines · 71 tokens per session scan A 0abf1917a09e
weekly-account-review is a skill published in the GitHub repository sdaluga/claude-cowork-playbook (2 stars, last pushed 15d ago), licensed MIT. It adds 71 tokens to every session and 1,059 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.
Other skills, from other repositories
brainstorming
Interactive spec generation — turn ideas into concrete specs with R-numbered requirements and testable acceptance criteria.
collaborating
Hackathon-native multiplayer collaboration mode -- brain-dump together, claim tasks across machines, flag decisions async. Drives the subcommands of /forge:collaborate.
executing
Autonomous task implementation workflow — implement, test, review, commit for each task in the frontier.
backpropagation
Trace runtime bugs back to spec gaps — identify missing acceptance criteria, update specs, generate regression tests, and detect patterns.
caveman-internal
Internal token optimization for Forge agent artifacts (handoff notes, artifact summaries, review notes). NOT exposed as a user-facing /caveman command.
design-system
DESIGN.md integration for Forge — ensures visual consistency across all UI tasks through standardized design specifications.