@open-agent-toolkit/cli 0.1.22 → 0.1.24

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,33 +0,0 @@
1
- ---
2
- title: CLI Utilities Overview
3
- description: Plain-language explanation of the OAT CLI surface that lives outside provider sync, docs tooling, and tracked workflows.
4
- ---
5
-
6
- # CLI Utilities Overview
7
-
8
- Not every OAT command belongs to a single product lane. Some commands are general-purpose setup, configuration, pack-management, or diagnostic utilities that support the rest of the toolkit without being specific to provider sync, docs tooling, or tracked workflow execution.
9
-
10
- That is what this section covers.
11
-
12
- ## What Lives Here
13
-
14
- - bootstrap and setup flows such as `oat init`
15
- - bundled pack management through `oat tools`
16
- - general configuration guidance
17
- - utility command groups for config, local state, diagnostics, and related inspection flows
18
-
19
- ## When To Use This Section
20
-
21
- Use CLI Utilities when:
22
-
23
- - you are first setting up OAT in a repo
24
- - you need to install or update OAT packs
25
- - you are looking for configuration or local-state inspection help
26
- - you need the general CLI surface without committing to one of the deeper lanes yet
27
-
28
- ## Continue Here
29
-
30
- - [CLI Bootstrap](bootstrap.md) for initial setup
31
- - [Tool Packs](tool-packs.md) for pack lifecycle management
32
- - [Configuration](configuration.md) for config semantics
33
- - [Config and Local State](config-and-local-state.md) for the wider utility command map
@@ -1,31 +0,0 @@
1
- ---
2
- title: Docs Tooling Overview
3
- description: Plain-language explanation of OAT docs support, docs app choices, and the index contract.
4
- ---
5
-
6
- # Docs Tooling Overview
7
-
8
- OAT can help bootstrap and maintain a structured docs surface, not just code and provider assets. The docs tooling is built around a simple contract: each directory owns an `index.md`, and that index owns a `## Contents` section that supports local discovery and generated navigation.
9
-
10
- OAT supports both Fumadocs and MkDocs. The site framework changes the surrounding app setup, but the underlying documentation contract stays the same.
11
-
12
- ## When To Use This Section
13
-
14
- Use Docs Tooling when:
15
-
16
- - you are adding a docs app to a repo
17
- - you need to keep index pages and nav structure in sync
18
- - you want a controlled analyze/apply loop for docs restructuring work
19
-
20
- ## Typical Flow
21
-
22
- 1. Bootstrap or adopt a docs app in the repo.
23
- 2. Use the docs commands to generate or sync index/navigation structure.
24
- 3. Apply the docs workflow when you want analysis-backed restructuring rather than ad hoc manual edits.
25
-
26
- ## Continue Here
27
-
28
- - [Add Docs to a Repo](add-docs-to-a-repo.md) for initial setup
29
- - [Commands](commands.md) for the CLI surface
30
- - [Workflows](workflows.md) for governed docs changes
31
- - [Docs Index Contract](../reference/docs-index-contract.md) for the underlying rules
@@ -1,38 +0,0 @@
1
- ---
2
- title: Provider Sync Overview
3
- description: Plain-language explanation of canonical assets, provider views, and the first-sync loop.
4
- ---
5
-
6
- # Provider Sync Overview
7
-
8
- Provider sync lets OAT manage one canonical set of agent assets and then project those assets into provider-specific views. In practice, that means you edit the canonical layout in `.agents/` and `.oat/`, then let OAT generate or reconcile the provider copies.
9
-
10
- This is useful when you want consistent instructions, skills, and rules across multiple providers without treating each provider directory as a long-lived hand-maintained source of truth.
11
-
12
- ## What OAT Treats As Canonical
13
-
14
- - canonical skills, agents, and rules under `.agents/`
15
- - sync state and related metadata under `.oat/`
16
- - provider-specific files as derived views unless they are explicitly adopted back into canonical form
17
-
18
- ## Typical Flow
19
-
20
- 1. Run `oat init` to create the base OAT layout and setup state.
21
- 2. Inspect current sync state with `oat status`.
22
- 3. Adjust provider enablement with `oat providers ...` if needed.
23
- 4. Run `oat sync` to materialize provider views from canonical assets.
24
- 5. Re-run `oat status` after edits to confirm whether anything drifted or needs adoption.
25
-
26
- ## When To Use This Section
27
-
28
- Use Provider Sync when:
29
-
30
- - you want to adopt OAT incrementally, without committing to tracked project workflows yet
31
- - you need a clear model for drift, strays, and adoption
32
- - you want to understand which files should be edited directly and which should be regenerated
33
-
34
- ## Continue Here
35
-
36
- - [CLI Bootstrap](../cli-utilities/bootstrap.md) for the first sync setup flow
37
- - [Scope and Surface](scope-and-surface.md) for the canonical/provider-view model
38
- - [Commands](commands.md) for the exact CLI behavior
@@ -1,38 +0,0 @@
1
- ---
2
- title: Agentic Workflows Overview
3
- description: Plain-language explanation of when to use tracked OAT projects versus direct CLI usage.
4
- ---
5
-
6
- # Agentic Workflows Overview
7
-
8
- OAT workflow mode adds a tracked lifecycle on top of the base CLI. Instead of just running commands directly, you work through explicit project artifacts such as `state.md`, `plan.md`, and `implementation.md`, with stable task IDs and review checkpoints.
9
-
10
- That extra structure is optional. You only need it when the work is large enough, risky enough, or long-lived enough that resumability and explicit coordination matter.
11
-
12
- ## When To Use Workflow Mode
13
-
14
- Use workflow mode when:
15
-
16
- - the work spans multiple sessions or contributors
17
- - you want explicit discovery, plan, implementation, and review artifacts
18
- - you need stable task sequencing and resumable execution
19
- - you want human-in-the-loop checkpoints around risky transitions
20
-
21
- Stay with direct CLI usage when:
22
-
23
- - the task is straightforward and bounded
24
- - you mainly need provider sync or a utility command
25
- - the overhead of project artifacts would outweigh the value
26
-
27
- ## Workflow Modes In Practice
28
-
29
- - CLI only: direct commands, no tracked project artifacts
30
- - Quick mode: tracked work with a lighter upfront planning path
31
- - Spec-driven mode: explicit discovery, requirements, design, and plan artifacts
32
- - Import mode: an externally-authored plan imported into OAT for tracked execution
33
-
34
- ## Continue Here
35
-
36
- - [Skills](skills/index.md) for task-oriented workflow skill discovery
37
- - [Ideas](ideas/index.md) for lightweight capture and refinement
38
- - [Workflow & Projects](projects/index.md) for the lifecycle, artifact, and review model