agent-gauntlet 0.1.4 → 0.1.6

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 CHANGED
@@ -18,34 +18,50 @@ Agent Gauntlet is designed to be "tool-agnostic" by leveraging the AI CLI tools
18
18
 
19
19
  ### Requirements
20
20
 
21
- - **Bun** (to run from source or build the compiled binary)
21
+ - **Bun** or **Node.js** (runtime)
22
22
  - **git** (change detection and diffs)
23
- - For review gates: one or more supported AI CLIs installed (`gemini`, `codex`, `claude`). For the full list of tools and how they are used, see [CLI Invocation Details](.docs/cli-invocation-details.md)
23
+ - For review gates: one or more supported AI CLIs installed (`gemini`, `codex`, `claude`). For the full list of tools and how they are used, see [CLI Invocation Details](docs/cli-invocation-details.md)
24
24
 
25
- ### Quick start
25
+ ### Installation
26
26
 
27
- - **Install dependencies**
27
+ You can install `agent-gauntlet` globally using `npm` or `bun`:
28
28
 
29
+ **Using npm:**
29
30
  ```bash
30
- bun install
31
+ npm install -g agent-gauntlet
31
32
  ```
32
33
 
33
- - **Build the CLI binary (recommended)**
34
-
34
+ **Using Bun (Recommended):**
35
35
  ```bash
36
- bun run build
36
+ bun add -g agent-gauntlet
37
37
  ```
38
38
 
39
+ ### Quick start
40
+
39
41
  - **Initialize configuration**
40
42
 
41
43
  ```bash
42
- ./bin/agent-gauntlet init
44
+ agent-gauntlet init
43
45
  ```
44
46
 
45
47
  - **Run gates**
46
48
 
47
49
  ```bash
48
- ./bin/agent-gauntlet
50
+ agent-gauntlet
51
+ ```
52
+
53
+ ### Development
54
+
55
+ - **Install dependencies**
56
+
57
+ ```bash
58
+ bun install
59
+ ```
60
+
61
+ - **Build the CLI binary**
62
+
63
+ ```bash
64
+ bun run build
49
65
  ```
50
66
 
51
67
  ### Basic usage
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-gauntlet",
3
- "version": "0.1.4",
3
+ "version": "0.1.6",
4
4
  "description": "A CLI tool for testing AI coding agents",
5
5
  "license": "Apache-2.0",
6
6
  "author": "Paul Caplan",
@@ -13,12 +13,12 @@ allowed-tools: Bash
13
13
  # /gauntlet
14
14
  Execute the autonomous verification suite.
15
15
 
16
- 1. Run \`npx agent-gauntlet run\` (or \`./bin/agent-gauntlet run\` if developing locally).
16
+ 1. Run \`agent-gauntlet run\`.
17
17
  2. If it fails, read the log files in \`.gauntlet_logs/\` to understand exactly what went wrong.
18
18
  3. Fix any code or logic errors found by the tools or AI reviewers, prioritizing higher-priority violations (critical > high > medium > low).
19
19
  4. If you disagree with AI reviewer feedback, briefly explain your reasoning in the code comments rather than ignoring it silently.
20
20
  5. Do NOT commit your changes yet—keep them uncommitted so the rerun command can review them.
21
- 6. Run \`npx agent-gauntlet rerun\` (or \`./bin/agent-gauntlet rerun\` if developing locally) to verify your fixes. The rerun command reviews only uncommitted changes and uses previous failures as context.
21
+ 6. Run \`agent-gauntlet rerun\` to verify your fixes. The rerun command reviews only uncommitted changes and uses previous failures as context.
22
22
  7. Repeat steps 2-6 until one of the following termination conditions is met:
23
23
  - All gates pass
24
24
  - You disagree with remaining failures (ask the human how to proceed)