let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update model guidance

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-06 23:48:25 +01:00
parent c920ee1166
commit edfc71a47e
2 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/models.md
View File

@@ -12,6 +12,10 @@ See [`docs/model-failover.md`](https://docs.clawd.bot/model-failover) for how au
Goal: give clear model visibility + control (configured vs available), plus scan tooling Goal: give clear model visibility + control (configured vs available), plus scan tooling
that prefers tool-call + image-capable models and maintains ordered fallbacks. that prefers tool-call + image-capable models and maintains ordered fallbacks.
## Model recommendations
Through testing, we’ve found Anthropic Opus 4.5 is the most useful general-purpose model for anything coding-related. We suggest GPT 5.2 Codex as another strong option. For personal assistant work, nothing comes close to Opus. If you’re going all-in on Claude, we recommend the Max $200 subscription: https://claude.com/pricing
## Command tree (draft) ## Command tree (draft)
- `clawdbot models list` - `clawdbot models list`

1
docs/security.md
View File

@@ -75,6 +75,7 @@ Even with strong system prompts, **prompt injection is not solved**. What helps
- Prefer mention gating in groups; avoid “always-on” bots in public rooms. - Prefer mention gating in groups; avoid “always-on” bots in public rooms.
- Treat links and pasted instructions as hostile by default. - Treat links and pasted instructions as hostile by default.
- Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem. - Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
- **Model choice matters:** we recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)). Using weaker models increases risk.
## Lessons Learned (The Hard Way) ## Lessons Learned (The Hard Way)