daily-standup — Claude Code skill: session standup report
Turns your recent Claude sessions into a standup report: work done per project, errors hit, what it cost.
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a claude-codeWhat daily-standup does
This skill pulls session data from Claude Agent Monitor and writes the standup for you. Sessions are grouped by working directory, so each project gets its own block. Every entry shows which tools ran and how the session ended.
A separate section covers trouble: sessions marked error or abandoned, failed tool calls, compaction events from hitting the context limit. Timing comes from session metadata — turn_count and total_turn_duration_ms — and the cost estimate from the pricing engine.
The data comes from a local API at http://localhost:4820: GET /api/sessions?limit=50 first, then GET /api/events?session_id={session_id} per session. If the monitor is not running on that port, the requests go nowhere. The argument is optional: nothing or “today” means the last 24 hours, “yesterday” the day before, or a date like “2025-04-10”.
What it helps with
- write a daily report without rereading every session by hand
- show which projects took the time
- spot sessions that errored out or were abandoned
- estimate what a day of agent work cost
- catch where the context limit was hit
Example prompts for the agent
- Generate my standup for today
- Build the session report for yesterday
- Show the standup for 2025-04-10
How to install daily-standup
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a claude-code2Manually: put the files in place
~/.claude/skills/daily-standup/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/daily-standup/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a codex2Manually: put the files in place
.agents/skills/daily-standup/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a cursor2Manually: put the files in place
.cursor/skills/daily-standup/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor daily-standup2Manually: put the files in place
.github/skills/daily-standup/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-productivity/skills/daily-standupManually: put the files in place
.devin/skills/daily-standup/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about daily-standup
How do I install daily-standup in Claude Code?
Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill daily-standup -a claude-code. The skill lands in ~/.claude/skills/daily-standup/SKILL.md.
What does daily-standup do?
It builds a standup report from Claude sessions: finished work grouped by project, errors and compaction events, plus time and cost metrics.
What does the skill need to run?
Claude Agent Monitor running at http://localhost:4820 — the skill reads sessions and events from its API.
Source text
SKILL.md · MIT
---
name: daily-standup
description: >
Generate a daily standup summary from recent Claude Code sessions — completed
work grouped by project (cwd), session costs from the pricing engine,
tool invocations, error/compaction/APIError events, and turn velocity
metrics from session metadata (turn_count, total_turn_duration_ms).
---
# Daily Standup
Generate a daily standup report from Claude Code Agent Monitor data.
## Input
The user provides: **$ARGUMENTS**
This may be:
- "today" or empty (default: last 24 hours)
- "yesterday" for the previous day
- A specific date: "2025-04-10"
## Procedure
1. **Fetch recent session data** from `http://localhost:4820`:
- `GET /api/sessions?limit=50` (default sort: most recently updated first)
- Filter sessions that started within the target day
- For each matching session: `GET /api/events?session_id={session_id}`
2. **Compile standup sections**:
### ✅ What I accomplished
- List each completed session with:
- Brief description (from session name or first tool's context)
- Working directory (project context)
- Key tools used and outcomes
- Duration and model used
- Group by project/working directory if multiple
### ⚠️ Issues encountered
- Sessions that ended in `error` or `abandoned` status
- Tools that failed (from error events)
- Compaction events (hit context limits)
- Unusually long sessions (>2x average duration)
### 📋 Key metrics
- Total sessions: N
- Total time spent: X hours Y minutes
- Tools invoked: N (top 3 listed)
- Estimated cost: $X.XX
- Completion rate: N%
### 🔮 Suggested focus areas
- Based on incomplete/error sessions, suggest what to revisit
- Based on tool patterns, suggest workflow improvements
3. **Format for standup**:
- Keep it concise — aim for a 2-minute read
- Lead with accomplishments
- Be honest about blockers
- Make metrics scannable
## Output Format
Present as a clean standup report with emoji section headers, bullet points for items, and a compact metrics table. Add a one-line summary at the top suitable for pasting into Slack or a team channel.
© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor