@monte3l/groundwork 1.1.0 → 1.1.1

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
@@ -385,7 +385,7 @@ the choice to you.
385
385
 
386
386
  `@monte3l/groundwork` follows [Semantic Versioning](https://semver.org/).
387
387
  Until 1.0.0, breaking changes ship in a `minor` release, as SemVer allows
388
- for major version zero -- see the changesets in this repo's history for
388
+ for major version zero -- see the changelog for
389
389
  examples. From 1.0.0, the public API is:
390
390
 
391
391
  1. **CLI flags, modes, and exit codes** -- `--help` lists every flag; exit
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@monte3l/groundwork",
3
- "version": "1.1.0",
4
- "description": "CLI that bootstraps a TypeScript project with a strict toolchain and Claude Code setup, or read-only surveys an existing one, plus a /customize plugin that tailors it to current guidance.",
3
+ "version": "1.1.1",
4
+ "description": "A CLI that sets up a TypeScript project with a strict toolchain and Claude Code, or surveys an existing one read-only, plus a /customize skill that tailors it to current guidance",
5
5
  "keywords": [
6
6
  "bootstrap",
7
7
  "claude-code",
@@ -42,6 +42,7 @@ Sources: [hooks](https://code.claude.com/docs/en/hooks),
42
42
  [hooks guide](https://code.claude.com/docs/en/hooks-guide),
43
43
  [managed settings](https://code.claude.com/docs/en/managed-settings),
44
44
  [mods events](https://code.claude.com/docs/en/plugins/mods/events),
45
+ [permissions](https://code.claude.com/docs/en/permissions#precedence-among-rules-hooks-and-mods),
45
46
  [sub-agents](https://code.claude.com/docs/en/sub-agents) and
46
47
  [agent teams](https://code.claude.com/docs/en/agent-teams).
47
48
 
@@ -63,16 +64,17 @@ Sources: [hooks](https://code.claude.com/docs/en/hooks),
63
64
  machine you don't control, run `/status` and read its "Setting sources"
64
65
  line: if `guard-hub-src-writes.mjs` and `guard-branch-isolation.mjs` aren't
65
66
  running, treat hub-and-spoke as an unenforced checklist.
66
- - **An installed mod sits below managed settings and above project hooks.** A
67
- mod that handles `tool.check` can approve a call a non-managed `PreToolUse`
68
- hook blocked, and project `PreToolUse` hooks run only after the last mod
69
- calls `next`. Only managed hooks outrank a mod. Check `/plugin` alongside
70
- `/status`.
67
+ - **An installed mod sits below managed settings and above project hooks.**
68
+ Project `PreToolUse` hooks run only after the last mod calls `next`, so a mod
69
+ that answers `tool.call` without it stops them running. A mod's `tool.check`
70
+ answers after the hooks: with managed settings or a Team or Enterprise
71
+ `/login` a call a `PreToolUse` hook blocked stays blocked, and with neither
72
+ the mod can approve it. Check `/plugin` alongside `/status`.
71
73
  - **Who counts as a writer.** The guard needs a writer-spoke `agent_type` and a
72
74
  non-empty `agent_id`. A fork subagent (on by default in every surface since
73
75
  Claude Code 2.1.302) is not a writer spoke, so unless its payload reports a
74
76
  writer `agent_type` it is treated as the hub (the docs don't say what a
75
- fork's payload carries). A fork cannot spawn further agents. With agent teams on, an in-process
77
+ fork's payload carries). At the depth limit a fork's `Agent` tool returns an error. With agent teams on, an in-process
76
78
  teammate has a documented `agent_id`; one built from a writer definition that
77
79
  also reports that `agent_type` passes as a writer. A split-pane teammate does
78
80
  not get `disallowedTools` (only an in-process one does), so every spoke's
@@ -101,7 +101,7 @@ prompt, or edit the hook's registration in `.claude/settings.json`.
101
101
  deployment (`managed-settings.json`, MDM, a console policy) outranks every file
102
102
  here, and `allowManagedHooksOnly` runs only managed hooks. An installed mod
103
103
  that handles `tool.check` can approve a call a project `PreToolUse` hook
104
- blocked, and only managed hooks outrank a mod. Nothing in the repo can detect
104
+ blocked, unless managed settings or a Team or Enterprise `/login` is in use. Nothing in the repo can detect
105
105
  either: on a machine you don't control, check `/status` ("Setting sources") and
106
106
  `/plugin` before trusting `guard-hub-src-writes.mjs` and
107
107
  `guard-branch-isolation.mjs`. Detail and sources:
@@ -41,7 +41,7 @@
41
41
  "@commitlint/types": "^21.2.0",
42
42
  "@eslint/js": "^10.0.1",
43
43
  "@types/node": "^24.13.3",
44
- "@vitest/coverage-v8": "^5.0.2",
44
+ "@vitest/coverage-v8": "^5.0.5",
45
45
  "eslint": "^10.11.0",
46
46
  "eslint-import-resolver-typescript": "^4.4.5",
47
47
  "eslint-plugin-import-x": "^4.17.1",
@@ -53,6 +53,6 @@
53
53
  "publint": "^0.3.24",
54
54
  "typescript": "^6.0.3",
55
55
  "typescript-eslint": "^8.71.0",
56
- "vitest": "^5.0.2"
56
+ "vitest": "^5.0.5"
57
57
  }
58
58
  }
@@ -17,8 +17,9 @@ templates/packs/<name>/
17
17
  ```
18
18
 
19
19
  A pack has no release of its own: it ships inside the CLI tarball, so a change
20
- to one that is user-visible takes a CLI changeset whose summary starts with
21
- `pack(<name>):`. The checklist for working on a pack lives in the source
20
+ to one that is user-visible is released by its Conventional Commit type
21
+ (`fix(packs): ...` for a fix or a change to existing behaviour,
22
+ `feat(packs): ...` for new public surface; there is no changeset). The checklist for working on a pack lives in the source
22
23
  repository's own `.claude/rules/pack-<name>.md` (m3l-groundwork, not shipped),
23
24
  not in the pack, since a pack cannot ship a rule (see below).
24
25
 
@@ -86,7 +86,7 @@ jobs:
86
86
  fetch-depth: 0
87
87
 
88
88
  - id: claude
89
- uses: anthropics/claude-code-action@db77d4d3c98f3f6380e7cd45ffba2342a3dbde3c # v1.0.254
89
+ uses: anthropics/claude-code-action@6b6870e649b5ff408753befeaee5fc7989d4e6a9 # v1.0.258
90
90
  with:
91
91
  anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
92
92
  # Swap in CLAUDE_CODE_OAUTH_TOKEN or the Workload Identity
@@ -67,7 +67,7 @@ jobs:
67
67
  fetch-depth: 1
68
68
 
69
69
  - name: Run Claude Code
70
- uses: anthropics/claude-code-action@db77d4d3c98f3f6380e7cd45ffba2342a3dbde3c # v1.0.254
70
+ uses: anthropics/claude-code-action@6b6870e649b5ff408753befeaee5fc7989d4e6a9 # v1.0.258
71
71
  with:
72
72
  # Option 1 (active default): a stored API key. Install the Claude
73
73
  # GitHub App (https://github.com/apps/claude) and add
@@ -97,7 +97,11 @@ jobs:
97
97
  # Optional: customize the trigger phrase (default: @claude)
98
98
  # trigger_phrase: "/claude"
99
99
 
100
- # Optional: configure Claude's behavior with CLI arguments
101
- # claude_args: |
102
- # --max-turns 10
100
+ # Cap each run at 20 turns so a runaway loop stops well before the
101
+ # 30-minute job timeout (Anthropic's cost guidance recommends
102
+ # setting one). Raise it if larger tasks hit the cap.
103
+ claude_args: |
104
+ --max-turns 20
105
+ # Further CLI arguments go in the same block, for example, at the
106
+ # same indentation as `--max-turns 20`:
103
107
  # --allowedTools "Bash(npm install),Bash(npm run build),Bash(npm run test:*)"