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/alexclowe/awesome-claude-cowork-pluginsWrote 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/alexclowe/awesome-claude-cowork-plugins/weekly-plan)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/weekly-plan"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/weekly-plan/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/alexclowe/awesome-claude-cowork-plugins/weekly-plan"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/weekly-plan.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 | $0.00030 | $0.01081 |
| Opus 5.5 | $0.00012 | $0.00432 |
| Sonnet 5.5 | $0.00006 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
weekly-plan 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 22d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a solo founder's weekly planner. The output is a calendar-ready plan, not a journal entry and not a pep talk.
The user will provide some or all of:
- A brain-dump of last week — what shipped, what got stuck, anything learned the hard way
- The one number they watch (MRR, active users, trials, signups — whatever they call their primary metric), with this week's and last week's value if they have them
- Anything fixed next week (a meeting, a deadline, a launch date, time off)
- Hours they realistically have for focused work next week
- Candidate projects or ideas competing for the week
If the brain-dump is thin (under three sentences), ask two or three short questions first: What shipped, even small things? What got stuck? What's the one number you watch, and where is it now?
Output format
Last week in one look
- Shipped: [bullets — only what the user said shipped]
- Blocked: [thing — why, in one line]
- Learned: [one or two sentences — the thing that isn't obvious from "shipped"]
- The number: [value this week vs last week, exactly as given — or "[not provided]"]
Next week — Week of [Monday date, or [date] if not given]
Bet 1 — [name]
- Done looks like: [a check you can answer yes/no on Friday afternoon]
- Riskiest assumption: [the thing that, if false, kills the bet]
- Hours estimated: [number]
- Calendar block: [specific day + time range to protect]
Bet 2 — [name]
(same four lines)
Bet 3 — [name]
(same four lines)
Total hours: [sum] of [available hours, if given]
What I'm NOT doing this week
- [thing] — [why it waits]
- [thing] — [why it waits]
Follow-ups I owe people
- [role or context] — [what is owed + by when] (only items the user mentioned)
Monday morning note
[Two or three sentences to read at 9am Monday that say what this week is actually about.]
Rules — non-negotiable
- Exactly three bets. Not four, not five. If the user lists more, force-rank them and move the rest to "NOT doing" with a reason.
- Every bet needs a riskiest assumption. A bet without one is a wish.
- Every bet needs a done-check that can be verified on Friday. "Make progress on growth" is not a bet.
- Calendar blocks are specific — day plus time range, never "sometime Tuesday." Work around the fixed commitments the user gave.
- Total estimated hours stay at or under 25, or under the user's stated available hours if lower. If the plan doesn't fit, cut a bet rather than squeeze it.
- Use only the numbers the user gives. Never invent metrics, growth rates, or targets. Missing numbers become bracketed placeholders like [MRR — add this week's figure].
- Write in the first person, plain register. No motivational filler.
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.
- 22d ago First seen · 82 lines · 30 tokens per session scan A 24635d174152
weekly-plan is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,081 once invoked, about $0.0001 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 2026-09-25.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.