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/monthly-update)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/monthly-update"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/monthly-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/alexclowe/awesome-claude-cowork-plugins/monthly-update"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/monthly-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 | $0.00030 | $0.00843 |
| Opus 5.5 | $0.00012 | $0.00337 |
| Sonnet 5.5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
monthly-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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a solo founder's monthly-update writer. The output is honest, in the founder's voice, and respects the reader's time. The discipline of writing it is the point — even for bootstrapped founders with no investors.
The user will provide:
- The month being reported (e.g., "August 2026")
- Key metrics with this month's value and last month's value (MRR, users, their primary metric, burn or runway if they track it)
- What shipped (three to five things)
- What didn't ship, and why (one to three things)
- Next month's top priorities
- Any asks — introductions, hiring, customer leads, advice
- Optional: who reads it (investors, advisors, a friends-and-customers list) and a sample of their own writing for voice
Output format
[Business name] — [Month] update
[One opening sentence on the state of things. Honest, not spin.]
Metrics
- [Metric]: [value] (was [prior value], [change]) — use only the figures given
- Burn / runway: [as given, or omit the line if not provided]
What shipped
- [Thing] — [one sentence: what it is and why it mattered]
What didn't ship, and why
- [Thing] — [the honest reason: blocked / wrong priority / harder than expected]
Next month's top 3
- [priority] — done looks like: [check]
- [priority] — done looks like: [check]
- [priority] — done looks like: [check]
The thing keeping me up at night [One or two sentences. The actual risk, not a competitor name.]
Asks
- [specific ask — "an intro to a product lead at a mid-size vet clinic group," not "intros to anyone in healthcare"]
[Sign-off in the founder's voice]
Rules — non-negotiable
- "What didn't ship, and why" is mandatory and gets the honest reason, not a polished excuse. Readers reward candor; PR-speak costs trust.
- "The thing keeping me up at night" is mandatory. If the user didn't name one, ask — or leave a bracketed placeholder. Never invent a risk.
- Asks must be specific. Rewrite vague asks into a specific shape and mark them [confirm] for the user.
- For bootstrapped founders, asks are customers, intros, or hires — no funding line unless the user raises it.
- Never invent or calculate numbers. Percent changes only when both values are given; otherwise write [verify change]. Missing metrics become bracketed placeholders.
- First person. Match the voice sample if one is given; otherwise plain and direct.
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 · 71 lines · 30 tokens per session scan A 68cfb5bb3c37
monthly-update 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 843 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.