Skip to main content
plugin

standup-autopilot — Claude Code plugin for standup reports

The standup-autopilot plugin turns agent session transcripts into a daily standup card with tasks, tests, PRs, and blockers. Open blockers carry into the next session.

MIT ★ 586 updated 2026-10-26

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add karanb192/claude-code-hooks
/plugin install standup-autopilot@claude-code-hooks
Open on GitHub

What standup-autopilot does

When Stop or SessionEnd fires, the plugin records a session summary in that day’s JSONL ledger: the task, branch and diffstat, test commands with exit codes, PRs, and unresolved blockers. Both events update the entry by session_id, so a session is not counted twice. Run /standup-autopilot:standup to render today’s card, with a line for each repository.

At SessionStart, open blockers from the previous day are added to the agent’s context. The first session of the day also prints a standup card to stderr. Records come from local session transcripts; strings that resemble credentials are removed before anything is written. The plugin makes no network requests. Its ledgers and hook logs live under ~/.claude/standup/ and ~/.claude/hooks-logs/; Claude Code hook events are required.

What it helps with

  • draft a cross-repository standup from agent sessions
  • collect test results and PR references from transcripts
  • bring yesterday’s unresolved blockers into the next session
  • render a standup card from the current day’s ledger

Example prompts for the agent

  • Render today’s standup card with /standup-autopilot:standup.
  • Show the tasks, tests, and PRs recorded for each repo with /standup-autopilot:standup.
  • Carry yesterday’s unresolved blockers into the next session’s context.

How to install standup-autopilot

Plugin marketplace

/plugin marketplace add karanb192/claude-code-hooks
/plugin install standup-autopilot@claude-code-hooks

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about standup-autopilot

How do I install standup-autopilot in Claude Code?

Run these commands in order: /plugin marketplace add karanb192/claude-code-hooks, then /plugin install standup-autopilot@claude-code-hooks. Restart Claude Code after installation.

What does standup-autopilot do?

It records agent session outcomes and renders a daily standup card grouped by repository. Unresolved blockers from the previous day are added to the next session’s context.

Where does standup-autopilot store its data?

Daily session ledgers are kept in ~/.claude/standup/, and hook logs in ~/.claude/hooks-logs/. Credential-like strings are redacted before writing, and the plugin makes no network calls.

Source text

standup-autopilot · MIT
# standup-autopilot

> Writes your daily standup from what your agents actually did across your repos: tasks, tests, PRs, and blockers pulled from session transcripts, not commits or tickets.

On every `Stop` and `SessionEnd`, it parses the session transcript and snapshots the outcome (task summary, git branch and diffstat, test commands with exit codes, opened PRs, and unresolved blockers) to a per-day JSONL ledger. Both events run the same idempotent upsert keyed by `session_id`, so whichever fires last wins. On `SessionStart` (startup), it re-injects the previous ledger day's open blockers into the agent via `additionalContext` and prints a standup-ready card to stderr on the first session of the day. Credential-shaped strings (`ghp_`/`sk-`/`xox` tokens, AWS keys, JWTs, `key=value` secrets) are redacted before anything is written to disk.

## Install

```
/plugin marketplace add karanb192/claude-code-hooks   # once per machine
/plugin install standup-autopilot@claude-code-hooks
```

Restart Claude Code, done. (Or from a shell: `claude plugin install standup-autopilot@claude-code-hooks`.)

## What it does

| Event | Runs | What happens |
| --- | --- | --- |
| `SessionStart` (matcher: `startup`) | sync | Re-injects the previous ledger day's unresolved blockers via `additionalContext`; on the first session of the day, prints a standup card to stderr. |
| `Stop` | async (zero added latency) | Snapshots the session's outcome (task, branch + diffstat, tests + exit codes, PRs, blockers) to the day's ledger. |
| `SessionEnd` | sync | Runs the same idempotent upsert as `Stop`, capturing the session's final state. |

`/standup-autopilot:standup` renders today's standup card: one line per repo (what got done, tests run, PRs, diffstat) plus any unresolved blockers, restated as a ready-to-paste update.

## Configuration

No configuration needed. State lives in `~/.claude/standup/<YYYY-MM-DD>.jsonl` (append-only per-day ledgers, deduped on read by `session_id`); hook run logs go to `~/.claude/hooks-logs/<YYYY-MM-DD>.jsonl`.

## Data & privacy

Recorded: task summaries, git branch/diffstat, test commands and exit codes, PR references, and blocker snippets, all derived from your local session transcripts, with credential-shaped strings redacted before write. Everything stays on your machine; the plugin makes no network calls, ever.

## Uninstall

```
/plugin uninstall standup-autopilot@claude-code-hooks
```

© Karan Bansal · MIT · karanb192/claude-code-hooks

Similar plugins

All plugins for Notes, tasks and projects →

From the same set28

The whole set →
git-safety git-safety — a PreToolUse Bash hook for Claude Code that intercepts destructive git and gh CLI actions before execution. ★ 586repo stars protect-secrets protect-secrets — a PreToolUse hook that checks every Read, Edit, Write, Bash and Grep call and blocks .env, SSH keys or cloud credentials — or asks you first. ★ 586repo stars bounty-board bounty-board turns TODO and FIXME comments into bounties that grow in XP value as they age. Scans your repo, prices each debt marker by git-blame age, and feeds the top 3 into your session as side quests. ★ 586repo stars dead-end-registry dead-end-registry stores reverted code changes and alerts you before retrying failed ideas. Keeps track of discarded approaches and detour token costs per repository. ★ 586repo stars pr-provenance-stamp pr-provenance-stamp appends a provenance receipt to your pull request body: prompts, estimated spend, test exit codes and an agent-versus-human line split. ★ 586repo stars dead-rules-audit dead-rules-audit tracks how Claude Code adheres to CLAUDE.md rules during edits and flags chronically violated items. ★ 586repo stars nerf-receipts The nerf-receipts plugin tracks tool failures, repeated edits to the same file, and tokens per task. Use it to see whether those signals shift when the model changes. ★ 586repo stars cache-tax cache-tax prices a cold return to a session before you send the next message, so a lapsed 1-hour prompt cache does not quietly re-write the whole context. ★ 586repo stars

Project sponsors

Companies that keep this analytics open