openclawd/config
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
config/TOOLS.md

9.6 KiB
Raw Permalink Blame History

TOOLS.md - Local Notes

Skills define how tools work. This file is for your specifics — the stuff that's unique to your setup.

Model Selection Policy

When creating tasks, jobs, sub-agents, or hooks, choose the appropriate model:

Model Use For
Opus 4.6 Everything (default) - best quality, same limits as Sonnet in Max plan
Haiku 4.5 Simple bulk tasks only - news summaries, quick lookups, translations

Default (main session): Opus 4.6 Sonnet 4.5: Not used (Opus has same limits but better quality)

Home Assistant Integration

  • Webhook endpoint: /hooks/agent
  • Token: configured in hooks.token
  • Model: Opus 4.5 (default)

Arrival Hook

When user arrives home, HA calls the webhook. Check memory/arrival-reminders.json for pending reminders and deliver them.

Important: Just send the content directly — no explaining what you're doing (checking files, clearing reminders, etc.). User just wants the info, not the process.

File format for memory/arrival-reminders.json:

{
  "reminders": [
    { "id": "unique-id", "task": "fetch_weather_tomorrow" },
    { "id": "unique-id", "task": "check_calendar_tomorrow" },
    { "id": "unique-id", "message": "Call mom! 📞" }
  ]
}
  • Use "task" for things that require action (fetch weather, check calendar, look something up)
  • Use "message" for simple reminders to display as-is
  • Always include a unique id for each item

Der Standard RSS

Helper script: ~/.openclaw/workspace/bin/derstandard

derstandard items [max]          # NEW items only (filters out seen)
derstandard items --all [max]    # All items including already seen
derstandard article <url>        # Full article content for a specific URL
derstandard articles <url1>,<url2>,... # Fetch multiple + auto-mark as seen
derstandard urls [max]           # Article URLs only (default: 50)
derstandard titles [max]         # Article titles only
derstandard seen                 # Show seen count and recent entries
derstandard reset                # Clear seen history
derstandard raw [max]            # Full RSS XML
  • Uses internal fivefilters proxy (bypasses web_fetch private IP block)
  • Pre-processes output for minimal token usage
  • Auto-tracks seen articles in memory/derstandard-seen.txt
  • items marks ALL displayed URLs as seen (even if skipped)
  • Auto-prunes to 200 entries (oldest removed)

Workflow for news briefing:

  1. derstandard items → shows NEW articles, marks them as seen
  2. Pick interesting ones, optionally fetch full content with articles
  3. Next briefing: only shows articles published since last check

Audiobookshelf

Helper script: ~/clawd/bin/audiobooks

audiobooks current              # Currently listening / in-progress books
audiobooks recent [limit]       # Recently active books (default: 5)
audiobooks finished [limit]     # Finished books (default: 10)
audiobooks stats                # Listening stats overview
audiobooks libraries            # List libraries
audiobooks library [limit]      # All books with metadata (--full for full descriptions)
audiobooks genres               # List genres with counts
  • Credentials: .credentials/services.env
  • URL: https://audiobooks.cloonar.com
  • Output is tab-separated for minimal tokens
  • Use during wind-down to suggest continuing audiobook

Jellyfin

Helper script: ~/clawd/bin/jellyfin

jellyfin resume [limit]         # Continue watching (in-progress items)
jellyfin recent [limit]         # Recently added to library
jellyfin watched [limit]        # Watch history (last played)
jellyfin shows                  # All series with watch status
jellyfin movies                 # All movies with watch status
jellyfin search <query>         # Search library
jellyfin stats                  # Watch statistics overview
jellyfin libraries              # List libraries
jellyfin library [limit]        # All movies & shows with metadata (--full for full descriptions)
jellyfin genres                 # List genres with counts
  • Credentials: .credentials/services.env (user-scoped token for tv)
  • URL: https://jellyfin.cloonar.com
  • Output is tab-separated for minimal tokens
  • Use during wind-down to suggest specific shows/movies

Forgejo Git Access

Helper script: ~/.openclaw/workspace/bin/forgejo

forgejo repos [org]              # List repos
forgejo files <owner/repo> [path] # List files
forgejo cat <owner/repo> <path>  # Get file content
forgejo issues <owner/repo>      # List open issues
forgejo prs <owner/repo>         # List open PRs
forgejo branches <owner/repo>    # List branches
forgejo commits <owner/repo> [n] # Recent commits
forgejo search <query>           # Search repos
forgejo raw <endpoint>           # Raw API call
  • URL: https://git.cloonar.com
  • User: openclawd (read-only)
  • Credentials: .credentials/services.env

CalDAV Calendar Access

Helper script: ~/.openclaw/workspace/bin/calendar

calendar today              # Today's events (default)
calendar tomorrow           # Tomorrow's events
calendar week               # Next 7 days
calendar next               # Next 14 days
calendar month              # Next 30 days
calendar date 2026-02-20    # Events on a specific date
calendar 2026-02-20         # Shorthand for date
calendar range 2026-02-18 2026-02-25  # Date range
calendar search dentist     # Search by name/location (next 90 days)
calendar search rpg 180     # Search with custom day range
  • Credentials: .credentials/services.env (NEXTCLOUD_URL, NEXTCLOUD_USER, NEXTCLOUD_PASS, CALDAV_CALENDAR)
  • Calendar: personal_shared_by_dominik.polakovics@cloonar.com
  • Output: tab-separated (time, summary, location)
  • Times shown in Vienna timezone

AI News RSS (Hybrid Approach)

Helper script: ~/.openclaw/workspace/bin/ainews

ainews items [max]          # NEW items only (filters out seen)
ainews items --all [max]    # All items including already seen
ainews article <url>        # Full article content via fivefilters
ainews articles <url1>,<url2>,... # Fetch multiple + auto-mark as seen
ainews seen                 # Show seen count and recent entries
ainews reset                # Clear seen history
  • Aggregates: Simon Willison, OpenAI Blog, Sebastian Raschka
  • Auto-tracks seen articles in memory/ainews-seen.txt
  • Auto-prunes to 200 entries

Content availability by source:

Source Full Content Method
Simon Willison ✅ In RSS/fivefilters ainews articles
Sebastian Raschka ✅ In RSS/fivefilters ainews articles
OpenAI Blog ❌ JS-rendered Use web_fetch tool

Hybrid workflow for AI news briefing:

  1. ainews items → shows NEW articles from all sources
  2. For Simon/Raschka: ainews articles <urls> to get full content
  3. For OpenAI: Use web_fetch tool directly (fivefilters can't extract JS sites)
  4. Write briefing with all content

Brain Dump CLI

Helper script: ~/clawd/bin/tasks

tasks list [--priority now,soon] [--due] [--limit N]
tasks add --text "..." --priority soon [--context "..."]
tasks add --recurring --text "..." --frequency daily [--when evening] [--context "..."]
tasks edit <id> [--text "..."] [--priority|--frequency|--when|--context "..."]
tasks done <id>
tasks show <id>
tasks nudged <id1>,<id2>,...
tasks recurring
  • Data: memory/tasks.json
  • --due filters by nudge interval: now=1d, soon=3d, someday=7d
  • nudged marks tasks as just-nudged (resets due timer)
  • recurring lists all recurring items with full context (note, when, frequency)
  • add --recurring / edit / done work for both tasks and recurring items
  • Output is tab-separated for minimal tokens

Heartbeat workflow:

  1. tasks list --due --limit 2 → get tasks needing a nudge
  2. Mention them conversationally
  3. tasks nudged <id1>,<id2> → mark as nudged

Finnhub Stock Market API

Helper script: ~/.openclaw/workspace/bin/stonks

stonks quote <symbol>              # Current price
stonks search <query>              # Search for symbols
stonks candles <symbol> [days]     # Price history (default: 30)
stonks news <symbol> [days]        # Company news (default: 7)
stonks profile <symbol>            # Company info
stonks portfolio                   # Show virtual portfolio
stonks buy <symbol> <amount>       # Virtual buy (EUR)
stonks sell <symbol> [amount]      # Virtual sell (EUR or all)
stonks limit-buy <sym> <price> <amt>   # Limit buy order
stonks limit-sell <sym> <price> [amt]  # Limit sell order
stonks check-limits                # Check & execute triggered limits
stonks history                     # Trade history
  • Credentials: .credentials/services.env (global env file — ALL new credentials go here, never create separate env files)
  • Portfolio data: memory/portfolio.json
  • Virtual starting capital: €1,000
  • N26 constraint: Only trade instruments available on N26 (check with user)
  • Symbols: Use Finnhub format (e.g., RHM.DE for Xetra, AAPL for NASDAQ)

Portfolio management:

  • Check limits during morning briefing and heartbeats
  • Include portfolio status in morning briefing and weekly review
  • Be proactive about market-moving news affecting positions

Scheduled Briefings

Briefing Schedule Content
Morning Briefing Daily 9:00 Vienna Calendar, weather, tasks, portfolio (NO news)
Weekly Review Sunday 18:00 Vienna Week recap, open tasks, portfolio performance, next week preview

News briefings (Der Standard, AI News) are DISABLED. Do not send them during heartbeats or morning briefings.

Add whatever helps you do your job. This is your cheat sheet.