with one click
briefing
// Executive daily briefing aggregating reports from all agents into decision-focused summary. Triggers: briefing, daily summary, status across system, executive update.
// Executive daily briefing aggregating reports from all agents into decision-focused summary. Triggers: briefing, daily summary, status across system, executive update.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | briefing |
| description | Executive daily briefing aggregating reports from all agents into decision-focused summary. Triggers: briefing, daily summary, status across system, executive update. |
| effort | medium |
| disable-model-invocation | true |
| agent | chief-of-staff |
| context | fork |
| allowed-tools | Read, Grep, Glob |
Triggers the Chief of Staff to generate an executive summary.
/briefing [period]
# Example: /briefing today
# Example: /briefing week
/briefing --tokens [--since 7d|24h|30m]
# Reports real session token usage from Claude Code JSONL.
kb/learnings/, maintenance/ logs, and recent runs.## Daily Brief — 2026-04-23
### Ops
- night-watch: 3 dep updates shipped, 1 rolled back (breaking change in `x-pkg@2.0`)
- health: all green except `mailpit` (degraded, non-critical)
### Strategy
- predict: new PR #42 overlaps with in-flight refactor in `/src/auth`
### Actions needed
- Review rollback from night-watch (ETA: 5 min)
- Decide on `x-pkg` pin strategy (open question on GitHub #41)
kb/learnings/ often mixes drafts with completed entries. Filter by frontmatter status: final or by filename convention before aggregating.maintenance/ branch logs from /night-watch use a different format (Shift Report markdown) than agent run logs. Do not concatenate blindly — parse each source separately and normalize.--since or a date filter, or you will read a week into yesterday's memory.The --tokens flag reports real token usage parsed from Claude Code session JSONL — not estimates. Useful for:
output-mode: concise actually reduces tokens vs default sessionsUnderlying script: scripts/session_token_stats.py.
# Aggregate current session
python3 scripts/session_token_stats.py --json
# Statusline-friendly one-line output
python3 scripts/session_token_stats.py --statusline
# Trend vs baseline
python3 scripts/session_token_stats.py --statusline --baseline ~/.softspark/ai-toolkit/baseline.json
ai-toolkit install wires ~/.claude/settings.json to app/hooks/ai-toolkit-statusline.sh. The hook reads native Claude Code statusLine stdin (no session JSONL parsing) and renders one line:
➜ <dir> git:(branch) ✗ ████░░░░░░ 43% ↑6.5k ↓252k effort:xhigh <model>
Segments left to right:
➜ <dir> — current directory basenamegit:(branch) ✗ — git branch + dirty marker<70%, orange 70–89%, red ≥90%↑in ↓out — token arrows. Green up = input (upload), red down = output (download). Both cumulative across the session.effort:level — Claude Code effort level (low / medium / high / xhigh)Custom statusLine entries you set yourself (without the _source: ai-toolkit tag) are preserved untouched on install.
Opt-outs (no reinstall required):
AI_TOOLKIT_STATUSLINE_DISABLE=1 — silence the line entirelyAI_TOOLKIT_STATUSLINE_NO_TOKENS=1 — hide token arrows segmentAI_TOOLKIT_STATUSLINE_NO_GIT=1 — hide git segmentAI_TOOLKIT_STATUSLINE_NO_EFFORT=1 — hide effort level segmentAI_TOOLKIT_STATUSLINE_NO_COLOR=1 — disable ANSI colorsAI_TOOLKIT_STATUSLINE_SHOW_COST=1 — append Claude Code's reported cost (cost.total_cost_usd)AI_TOOLKIT_STATUSLINE_DUMP=1 — write received stdin to /tmp/cc-statusline-input.json (debug)python3 scripts/session_token_stats.py --json | jq '.totals' > ~/.softspark/ai-toolkit/baseline.json
export AI_TOOLKIT_STATUSLINE_BASELINE=~/.softspark/ai-toolkit/baseline.json
The statusline then renders trend arrows (↑ / ↓) against that baseline.
/workflow incident-responsekb/learnings/<agent>/)/plan or /prd-to-plan/health