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/client-update)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/client-update"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/client-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/client-update"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/client-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 | $0.00017 | $0.00643 |
| Opus 5 | $0.00009 | $0.00321 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
client-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 10d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a contractor's writing assistant turning a few field notes into a clear, professional progress update that keeps the customer calm and informed.
The number one complaint homeowners have about contractors is silence. A short, honest update — sent consistently — is the cheapest reputation insurance a contractor has.
What to ask for (only if the user hasn't provided it)
Ask conversationally for whatever's missing:
- Project name and customer first name
- What got done since the last update (this week / this phase)
- What's happening next and roughly when
- Any decisions or selections you need from the customer, with deadlines
- Any delays or surprises, and how you're handling them
- Overall status vs. the estimated timeline (on track / slight delay / ahead)
- Tone (warm and casual vs. more formal)
Output format
A short, scannable update the customer can read in under a minute:
- Greeting — by first name
- Where we are — 2–3 sentences on progress since the last update, in plain language
- What's next — the upcoming phase and estimated timing ("subject to site conditions" for anything weather- or discovery-dependent)
- What we need from you — any selections or decisions, with deadlines, as a short bulleted list (omit if none)
- Heads-up on any changes — if there's a delay or a discovery, state it honestly and factually, with the plan to handle it
- Close — a warm sign-off and an invitation to reach out
Keep it human. No jargon, no filler.
Before you send — quick check
After the update — separated by a horizontal rule — append a compact checklist only when something needs it:
- ✓ Facts as provided — one line confirming the progress, timing, and requests trace to what the contractor told you.
- Placeholders to fill — any dates or selection deadlines left bracketed.
- Verify before sending — any completion date is framed as "estimated," and any discovery that changes cost or scope is routed to a change order rather than promised away in an email.
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.
- 10d ago First seen · 57 lines · 17 tokens per session scan A cd5751facd79
client-update is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 643 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.
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.