@iinm/plain-agent 1.7.22 → 1.7.23
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.
- package/README.md +6 -10
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,24 +2,20 @@
|
|
|
2
2
|
|
|
3
3
|
A lightweight CLI-based coding agent.
|
|
4
4
|
|
|
5
|
-
## Why Plain Agent?
|
|
6
|
-
|
|
7
5
|
- **Multi-provider** — Use Claude, GPT, Gemini, or any OpenAI-compatible model.
|
|
8
|
-
Switch providers without changing your workflow.
|
|
9
6
|
- **Fine-grained approval rules** — Auto-approve commands by name, arguments,
|
|
10
7
|
and file paths using regex patterns
|
|
11
|
-
([`config.predefined.json`](https://github.com/iinm/plain-agent/blob/main/config/config.predefined.json)).
|
|
12
|
-
- **Path validation** —
|
|
13
|
-
|
|
8
|
+
([`config.predefined.json#autoApproval`](https://github.com/iinm/plain-agent/blob/main/config/config.predefined.json)).
|
|
9
|
+
- **Path validation** — Restricts access to the working directory.
|
|
10
|
+
Git-ignored and untracked files require explicit approval.
|
|
14
11
|
- **Sandboxed execution** — Run the agent's shell commands inside a Docker
|
|
15
12
|
container with network access restricted to allowlisted destinations
|
|
16
13
|
(e.g., `registry.npmjs.org` only for `npm install`).
|
|
17
|
-
- **Extensible** — Define prompts and subagents in Markdown.
|
|
18
|
-
|
|
14
|
+
- **Extensible** — Define prompts and subagents in Markdown. Connect MCP servers.
|
|
15
|
+
Supports Claude Code plugins and `.claude/` commands, subagents, and skills.
|
|
19
16
|
|
|
20
17
|
## Limitations
|
|
21
18
|
|
|
22
|
-
- **CLI only** — Plain Agent does not provide a terminal UI.
|
|
23
19
|
- **Sequential subagent execution** — Subagents run one at a time rather than
|
|
24
20
|
in parallel. The trade-off is full visibility: every step is streamed to
|
|
25
21
|
your terminal so you can follow exactly what each subagent is doing.
|
|
@@ -491,9 +487,9 @@ Files are loaded in the following order. Settings in later files override earlie
|
|
|
491
487
|
|
|
492
488
|
The agent can use the following tools to assist with tasks:
|
|
493
489
|
|
|
494
|
-
- **exec_command**: Run a command without shell interpretation.
|
|
495
490
|
- **write_file**: Write a file.
|
|
496
491
|
- **patch_file**: Patch a file.
|
|
492
|
+
- **exec_command**: Run a command without shell interpretation.
|
|
497
493
|
- **tmux_command**: Run a tmux command.
|
|
498
494
|
- **ask_web**: Use the web search to answer questions that need up-to-date information or supporting sources. (requires Google API key or Vertex AI configuration).
|
|
499
495
|
- **ask_url**: Use one or more provided URLs to answer a question. Include the URLs in your question. (requires Google API key or Vertex AI configuration).
|