generate

generate is a command for Claude Code from AlexanderBZ/claude-status-update. It costs 12 tokens per session (800 once invoked), scanned A, original, MIT.

A command that turns recent Claude Code work sessions into a status update suitable for a daily standup, a short team progress meeting.

In plain words
What is it for?
Generating categorized reports of recent work over a chosen period, such as hours, days, or weeks.
Why use it?
It removes the need to review recent sessions and write a progress summary by hand.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the status-update plugin — 1 command shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AlexanderBZ/claude-status-update
Claude Code
/plugin install status-update

Made for: Claude Code.

Or install status-update, the plugin that ships this one along with the rest of its 1 command.

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 generate

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexanderbz/claude-status-update/generate.svg)](https://agentmods.dev/commands/alexanderbz/claude-status-update/generate)
Your own site
<a href="https://agentmods.dev/commands/alexanderbz/claude-status-update/generate"><img src="https://agentmods.dev/badge/commands/alexanderbz/claude-status-update/generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 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 $0.00012 $0.00800
Opus 5 $0.00006 $0.00400
Sonnet 5 $0.00002 $0.00160
Haiku 4.5 $0.00001 $0.00080

Measured 5d ago against content hash 65bff9cc9726, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

generate 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.

commands/generate.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Status Update

Generate a categorized standup report from recent Claude Code sessions.

Accepts an optional time range argument: a number followed by h (hours), d (days), or w (weeks). Examples: 24h, 7d, 2w. Defaults to 24h if omitted. Parse the argument into hours (e.g., 7d = 168, 2w = 336). Store the result as $HOURS for use in Step 2.

Step 1: Verify Python 3

Run python3 --version. If the command fails, try python --version instead. If neither succeeds, or the version is below 3.10, print:

Python 3.10+ is required but not installed. Install it from https://python.org and try again.

Then stop. Use whichever command succeeded (python3 or python) for all subsequent steps.

Step 2: Run the parser

Execute (using whichever Python command was found in Step 1):

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/status_update_parser.py" --hours $HOURS

The script writes .status-update/signals.json and prints the file path to stdout. Do not delete this file after reading.

Step 3: Read and parse signals

Use the Read tool to read .status-update/signals.json. Parse its contents as JSON. If the sessions array is empty, inform the user:

No Claude Code activity found in the specified time range.

Then stop.

Step 4: Summarize each session

For each session in the sessions array, spawn a Haiku subagent (model: "haiku") in parallel using the Agent tool. Provide the following prompt to each subagent, filling in the session signals:

You are a work-item extractor. Analyze the following signals from a single Claude Code session and identify each distinct piece of work performed.

Return ONLY a JSON array of objects. Each object has exactly two fields:
- "description": a concise summary of the work in imperative mood (e.g., "Fix login timeout", "Add dark mode toggle")
- "category": exactly one of "bug", "feature", "refactor", "research", or "other"

A single session may contain multiple work items spanning different categories. Combine closely related signals into one work item rather than listing each signal separately.

Do not include any text outside the JSON array. Do not wrap in markdown code fences.

Session signals:
$SESSION_SIGNALS

Read the full file on GitHub · 92 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 · 92 lines · 12 tokens per session scan A 65bff9cc9726

Subscribe to this mod's changes

generate is a command published in the GitHub repository AlexanderBZ/claude-status-update (5 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 800 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 2026-08-31.