tkmind/tkmind_go
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

docs: reorganize (#9310)

Browse Source
This commit is contained in:
Angie Jones
2026-05-18 13:38:14 -05:00
committed by GitHub
parent badb97a01e
commit bc9c1fc11a
54 changed files with 458 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files
documentation/docs/mcp/developer-mcp.md
+4 -4
View File
@@ -193,7 +193,7 @@ The Developer extension provides these tools:
You can layer multiple controls to match your risk tolerance and workflow:
- **[goose Permission Modes](/docs/guides/goose-permissions)** control when goose asks for approval:
- **[goose Permission Modes](/docs/guides/managing-tools/goose-permissions)** control when goose asks for approval:
| Mode | Description | Use Cases |
|------|-------------|-----------|
@@ -204,7 +204,7 @@ You can layer multiple controls to match your risk tolerance and workflow:
- **[Tool Permissions](/docs/guides/managing-tools/tool-permissions)** let you set `Always allow`, `Ask before`, and `Never allow` permissions for individual extension tools when in Manual Approval or Smart Approval modes
- **[.gooseignore files](/docs/guides/using-gooseignore)** restrict which files and directories goose can access (`.gitignore` files are fallback)
- **[.gooseignore files](/docs/guides/context-engineering/using-gooseignore)** restrict which files and directories goose can access (`.gitignore` files are fallback)
:::tip Changing Modes In-Session
You can change goose permission modes during a session without restarting:
@@ -218,13 +218,13 @@ You might want more control over goose's operations when working with sensitive
Here's an example configuration that enables oversight:
1. **Set the [permission mode](/docs/guides/goose-permissions)** to Smart Approval or Manual Approval:
1. **Set the [permission mode](/docs/guides/managing-tools/goose-permissions)** to Smart Approval or Manual Approval:
```yaml
# ~/.config/goose/config.yaml
GOOSE_MODE: smart_approve # or approve
```
2. **Create a [`.gooseignore` file](/docs/guides/using-gooseignore)** in your project to protect sensitive files:
2. **Create a [`.gooseignore` file](/docs/guides/context-engineering/using-gooseignore)** in your project to protect sensitive files:
```
.env*
secrets.*
documentation/docs/mcp/summon-mcp.md
+1 -1
View File
@@ -8,7 +8,7 @@ import TabItem from '@theme/TabItem';
import { PlatformExtensionNote } from '@site/src/components/PlatformExtensionNote';
import GooseBuiltinInstaller from '@site/src/components/GooseBuiltinInstaller';
The Summon extension lets you load knowledge into goose's context and delegate tasks to [subagents](/docs/guides/subagents).
The Summon extension lets you load knowledge into goose's context and delegate tasks to [subagents](/docs/guides/context-engineering/subagents).
You can load different types of sources:
- [**Skills**](/docs/guides/context-engineering/using-skills) - Reusable instruction sets that teach goose specific workflows
documentation/docs/mcp/tom-mcp.md
+1 -1
View File
@@ -16,7 +16,7 @@ The Top Of Mind extension injects custom text into goose's working memory every
Unlike system prompts or [goosehints](/docs/guides/context-engineering/using-goosehints) which can fade from attention as conversations grow, content injected by the tom extension appears fresh in every turn, making it more reliable for critical instructions.
:::tip
For a complete guide on use cases and best practices, see [Persistent Instructions](/docs/guides/using-persistent-instructions).
For a complete guide on use cases and best practices, see [Persistent Instructions](/docs/guides/context-engineering/using-persistent-instructions).
:::
## Configuration