chore(memory): reclassify topical notes into subfolders
This commit is contained in:
zap
218
memory/ops/2026-03-03-skill-toolbox.md
Normal file
218
memory/ops/2026-03-03-skill-toolbox.md
Normal file
@@ -0,0 +1,218 @@
|
||||
# Session: 2026-03-03 00:39:43 UTC
|
||||
|
||||
- **Session Key**: agent:main:main
|
||||
- **Session ID**: 3162e0eb-f33e-4629-b02c-1b58116e6b3f
|
||||
- **Source**: gateway:sessions.reset
|
||||
|
||||
## Conversation Summary
|
||||
|
||||
user: [Tue 2026-03-03 00:23 UTC] This swarm namespace is your's and it's shared with other future agents. Use it the way you want, just note that this is a small cluster made of Raspberry Pis, so keep that on mind when you deploy to it
|
||||
assistant: [[reply_to_current]] Perfect — understood and locked in.
|
||||
|
||||
I’ll treat `swarm` as shared, resource-constrained infra and default to:
|
||||
- lightweight containers
|
||||
- conservative CPU/RAM requests
|
||||
- minimal replicas
|
||||
- low-footprint background workloads
|
||||
|
||||
I also saved that Pi-cluster constraint in my local ops notes so I apply it by default.
|
||||
user: [Tue 2026-03-03 00:24 UTC] Nice!
|
||||
assistant: [[reply_to_current]] ⚡🙌
|
||||
user: [Tue 2026-03-03 00:25 UTC] What skills could we add to your "toolbox"?
|
||||
assistant: [[reply_to_current]] Great question. For your setup, high-value skills to add would be:
|
||||
|
||||
- **k8s-swarm-ops**
|
||||
Deploy/upgrade/rollback in `swarm`, with Pi-safe defaults (small requests, 1 replica unless needed).
|
||||
|
||||
- **k8s-debug-lite**
|
||||
Fast triage: pods/events/logs/restarts, plus “what changed” summaries.
|
||||
|
||||
- **minio-backup-manager**
|
||||
Scheduled backups, retention pruning, restore helpers for your `zap` bucket.
|
||||
|
||||
- **homelab-healthcheck**
|
||||
One-command status for Docker services, LAN reachability, disk/mem pressure, and alert summaries.
|
||||
|
||||
- **searxng-research-router**
|
||||
Prefer local SearXNG, fall back to Brave when needed, with source dedupe.
|
||||
|
||||
- **transcribe-pipeline**
|
||||
Route audio to `whisper-server`, return transcript + optional summarization/action items.
|
||||
|
||||
- **k8s-cost-footprint-guard**
|
||||
Prevent heavy deployments on Pi cluster (image size caps, request/limit policy checks).
|
||||
|
||||
- **secret-hygiene**
|
||||
Detect leaked keys/tokens in workspace and rotate/checklist workflows.
|
||||
|
||||
If you want, I can do this next:
|
||||
1) search ClawHub for existing matches,
|
||||
2) install the best candidates,
|
||||
3) scaffold missing ones as custom local skills.
|
||||
user: [Tue 2026-03-03 00:28 UTC] Let's add these skills
|
||||
assistant: On it — I’ll install the closest matching skills for each toolbox area and then report what mapped cleanly vs what needs a custom local skill.
|
||||
|
||||
assistant: [[reply_to_current]] Done — most are installed ✅
|
||||
|
||||
Installed successfully:
|
||||
- `kubernetes`
|
||||
- `openclaw-backup`
|
||||
- `openclaw-healthcheck-cron`
|
||||
- `searxng-local-search`
|
||||
- `cost-governor`
|
||||
- `api-credentials-hygiene`
|
||||
|
||||
Blocked (flagged as suspicious by ClawHub, requires explicit force):
|
||||
- `kubectl`
|
||||
- `faster-whisper-transcribe`
|
||||
|
||||
If you want, I can install those two with `--force` now, or I can build safer local equivalents instead.
|
||||
user: [Tue 2026-03-03 00:30 UTC] Build safer local equivalent
|
||||
assistant: [[reply_to_current]] Done — built safer local equivalents ✅
|
||||
|
||||
I created two local skills:
|
||||
|
||||
1) **`swarm-kubectl-safe`**
|
||||
- Path: `skills/swarm-kubectl-safe/`
|
||||
- Includes safe wrapper script:
|
||||
- `skills/swarm-kubectl-safe/scripts/kubectl-swarm.sh`
|
||||
- Enforces:
|
||||
- scoped kubeconfig (`~/.openclaw/credentials/kubeconfig-swarm.yaml`)
|
||||
- namespace `swarm`
|
||||
- blocks obviously dangerous cluster-wide delete commands by default
|
||||
|
||||
2) **`whisper-local-safe`**
|
||||
- Path: `skills/whisper-local-safe/`
|
||||
- Includes transcription script:
|
||||
- `skills/whisper-local-safe/scripts/transcribe-local.sh`
|
||||
- Uses local whisper server only (LAN), with endpoint fallback:
|
||||
- `/inference` then `/v1/audio/transcriptions`
|
||||
|
||||
I also validated the kubectl-safe wrapper is working (`namespace/swarm` check passed).
|
||||
|
||||
If you want, next I can add a tiny `zap-` deployment template generator under `swarm-kubectl-safe/scripts/` for one-command Pi-safe app deploys.
|
||||
user: [Tue 2026-03-03 00:33 UTC] Document these generated skills, why we didn't use the ones from ClawHub for security reasons, and we may revisit those skills
|
||||
assistant: [[reply_to_current]] Done ✅ — documented in all the right places.
|
||||
|
||||
I recorded it in:
|
||||
|
||||
- **`TOOLS.md`**
|
||||
- Added a **“Local custom skills (security-reviewed)”** section
|
||||
- Listed generated skills:
|
||||
- `skills/swarm-kubectl-safe`
|
||||
- `skills/whisper-local-safe`
|
||||
- Documented why we didn’t use flagged ClawHub skills (`kubectl`, `faster-whisper-transcribe`)
|
||||
- Added note that we can revisit after manual security review + explicit approval
|
||||
|
||||
- **`memory/2026-03-03.md`**
|
||||
- Logged the decision and rationale as today’s historical note
|
||||
|
||||
- **`MEMORY.md`**
|
||||
- Added long-term boundary note: avoid force-installing suspicious flagged skills unless explicitly approved after review
|
||||
|
||||
|
||||
assistant: 🧠 /context
|
||||
|
||||
What counts as context (high-level), plus a breakdown mode.
|
||||
|
||||
Try:
|
||||
- /context list (short breakdown)
|
||||
- /context detail (per-file + per-tool + per-skill + system prompt size)
|
||||
- /context json (same, machine-readable)
|
||||
|
||||
Inline shortcut = a command token inside a normal message (e.g. “hey /status”). It runs immediately (allowlisted senders only) and is stripped before the model sees the remaining text.
|
||||
assistant: 🧠 Context breakdown (detailed)
|
||||
Workspace: /home/openclaw/.openclaw/workspace
|
||||
Bootstrap max/file: 20,000 chars
|
||||
Bootstrap max/total: 150,000 chars
|
||||
Sandbox: mode=off sandboxed=false
|
||||
System prompt (run): 26,507 chars (~6,627 tok) (Project Context 14,047 chars (~3,512 tok))
|
||||
Injected workspace files:
|
||||
- AGENTS.md: OK | raw 7,804 chars (~1,951 tok) | injected 7,804 chars (~1,951 tok)
|
||||
- SOUL.md: OK | raw 1,664 chars (~416 tok) | injected 1,664 chars (~416 tok)
|
||||
- TOOLS.md: OK | raw 1,840 chars (~460 tok) | injected 1,840 chars (~460 tok)
|
||||
- IDENTITY.md: OK | raw 461 chars (~116 tok) | injected 461 chars (~116 tok)
|
||||
- USER.md: OK | raw 810 chars (~203 tok) | injected 810 chars (~203 tok)
|
||||
- HEARTBEAT.md: OK | raw 249 chars (~63 tok) | injected 249 chars (~63 tok)
|
||||
- BOOTSTRAP.md: MISSING | raw 0 | injected 0
|
||||
- MEMORY.md: OK | raw 531 chars (~133 tok) | injected 531 chars (~133 tok)
|
||||
Skills list (system prompt text): 2,604 chars (~651 tok) (6 skills)
|
||||
Skills: clawhub, healthcheck, mcporter, skill-creator, tmux, weather
|
||||
Top skills (prompt entry size):
|
||||
- healthcheck: 491 chars (~123 tok)
|
||||
- clawhub: 432 chars (~108 tok)
|
||||
- weather: 416 chars (~104 tok)
|
||||
- mcporter: 330 chars (~83 tok)
|
||||
- skill-creator: 296 chars (~74 tok)
|
||||
- tmux: 255 chars (~64 tok)
|
||||
Tool list (system prompt text): 1,937 chars (~485 tok)
|
||||
Tool schemas (JSON): 15,227 chars (~3,807 tok) (counts toward context; not shown as text)
|
||||
Tools: read, edit, write, exec, process, browser, canvas, nodes, message, tts, agents_list, sessions_list, sessions_history, sessions_send, sessions_spawn, subagents, session_status, web_search, web_fetch, memory_search, memory_get
|
||||
Top tools (schema size):
|
||||
- message: 4,277 chars (~1,070 tok)
|
||||
- browser: 1,921 chars (~481 tok)
|
||||
- nodes: 1,758 chars (~440 tok)
|
||||
- exec: 1,086 chars (~272 tok)
|
||||
- process: 961 chars (~241 tok)
|
||||
- web_search: 895 chars (~224 tok)
|
||||
- canvas: 661 chars (~166 tok)
|
||||
- edit: 591 chars (~148 tok)
|
||||
- sessions_spawn: 549 chars (~138 tok)
|
||||
- read: 392 chars (~98 tok)
|
||||
- web_fetch: 374 chars (~94 tok)
|
||||
- write: 313 chars (~79 tok)
|
||||
- sessions_send: 273 chars (~69 tok)
|
||||
- tts: 223 chars (~56 tok)
|
||||
- sessions_list: 212 chars (~53 tok)
|
||||
- subagents: 191 chars (~48 tok)
|
||||
- sessions_history: 161 chars (~41 tok)
|
||||
- memory_search: 139 chars (~35 tok)
|
||||
- memory_get: 128 chars (~32 tok)
|
||||
- session_status: 89 chars (~23 tok)
|
||||
- agents_list: 33 chars (~9 tok)
|
||||
Top tools (summary text size):
|
||||
- browser: 1,251 chars (~313 tok)
|
||||
- memory_search: 334 chars (~84 tok)
|
||||
- read: 298 chars (~75 tok)
|
||||
- session_status: 207 chars (~52 tok)
|
||||
- exec: 181 chars (~46 tok)
|
||||
- web_search: 175 chars (~44 tok)
|
||||
- tts: 152 chars (~38 tok)
|
||||
- memory_get: 151 chars (~38 tok)
|
||||
- sessions_spawn: 134 chars (~34 tok)
|
||||
- edit: 129 chars (~33 tok)
|
||||
- web_fetch: 129 chars (~33 tok)
|
||||
- write: 127 chars (~32 tok)
|
||||
- message: 124 chars (~31 tok)
|
||||
- agents_list: 118 chars (~30 tok)
|
||||
- nodes: 115 chars (~29 tok)
|
||||
- canvas: 106 chars (~27 tok)
|
||||
- subagents: 105 chars (~27 tok)
|
||||
- process: 85 chars (~22 tok)
|
||||
- sessions_send: 84 chars (~21 tok)
|
||||
- sessions_list: 54 chars (~14 tok)
|
||||
- sessions_history: 36 chars (~9 tok)
|
||||
Tools (param count):
|
||||
- message: 86 params
|
||||
- nodes: 36 params
|
||||
- browser: 29 params
|
||||
- canvas: 18 params
|
||||
- sessions_spawn: 13 params
|
||||
- exec: 12 params
|
||||
- process: 12 params
|
||||
- edit: 6 params
|
||||
- web_search: 6 params
|
||||
- sessions_send: 5 params
|
||||
- read: 4 params
|
||||
- sessions_list: 4 params
|
||||
- subagents: 4 params
|
||||
- write: 3 params
|
||||
- sessions_history: 3 params
|
||||
- web_fetch: 3 params
|
||||
- memory_search: 3 params
|
||||
- memory_get: 3 params
|
||||
- tts: 2 params
|
||||
- session_status: 2 params
|
||||
- agents_list: 0 params
|
||||
Session tokens (cached): 154,818 total / ctx=272000
|
||||
Inline shortcut: a command token inside normal text (e.g. “hey /status”) that runs immediately (allowlisted senders only) and is stripped before the model sees the remaining message.
|
||||
Reference in New Issue
Block a user