@monte3l/groundwork 1.0.3 → 1.0.5

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.
Files changed (37) hide show
  1. package/README.md +54 -12
  2. package/dist/assets.d.ts +22 -2
  3. package/dist/assets.js +40 -15
  4. package/dist/emit.js +3 -2
  5. package/dist/harness/rules.js +1 -1
  6. package/dist/main.js +5 -15
  7. package/dist/merge-json.d.ts +3 -1
  8. package/dist/merge-json.js +1 -1
  9. package/package.json +1 -1
  10. package/plugin/skills/customize/step-3-round-1.md +25 -17
  11. package/plugin/src/domain-map.ts +1 -1
  12. package/plugin/src/pack-map.ts +125 -44
  13. package/plugin/src/plugin-map.ts +1 -1
  14. package/templates/core/.claude/hooks/inject-decision-gate.mjs +4 -0
  15. package/templates/core/.claude/rules/agent-dispatch.md +46 -0
  16. package/templates/core/CLAUDE.md +41 -60
  17. package/templates/core/bin/check-exports.mjs +3 -1
  18. package/templates/core/bin/lib/harness-rules.mjs +1 -1
  19. package/templates/core/eslint.config.js +2 -0
  20. package/templates/core/vitest.config.ts +4 -3
  21. package/templates/packs/README.md +6 -3
  22. package/templates/packs/{github → claude-github}/files/.github/workflows/claude-pr-review.yml +1 -1
  23. package/templates/packs/{github → claude-github}/files/.github/workflows/claude.yml +1 -1
  24. package/templates/packs/claude-github/pack.json +19 -0
  25. package/templates/packs/github/pack.json +3 -3
  26. package/templates/packs/harness-extras/pack.json +3 -15
  27. package/templates/packs/licensing/pack.json +31 -0
  28. package/templates/packs/publishing/files/tools/release/_package-lock.json +914 -0
  29. package/templates/packs/publishing/pack.json +3 -14
  30. package/templates/packs/statusline/pack.json +31 -0
  31. package/templates/packs/supply-chain/pack.json +1 -1
  32. package/templates/packs/worktrees/pack.json +2 -1
  33. /package/templates/packs/{publishing → licensing}/files/REUSE.toml +0 -0
  34. /package/templates/packs/{publishing → licensing}/files/bin/check-license-headers.mjs +0 -0
  35. /package/templates/packs/{harness-extras → statusline}/files/.claude/hooks/statusline-layout.mjs +0 -0
  36. /package/templates/packs/{harness-extras → statusline}/files/.claude/hooks/statusline.mjs +0 -0
  37. /package/templates/packs/{harness-extras → statusline}/files/.claude/hooks/subagent-statusline.mjs +0 -0
@@ -11,6 +11,10 @@
11
11
  * instead of being discovered when `guard-branch-isolation.mjs` blocks a
12
12
  * src/test write on `main`.
13
13
  *
14
+ * It sees the line as typed: Claude Code runs `UserPromptSubmit` hooks before
15
+ * a skill or slash command expands (2.1.299), so `/creating-prs fix the lint`
16
+ * is judged on those words, and a bare `/starting-work` carries no change verb.
17
+ *
14
18
  * It is advisory: it emits `additionalContext` and exits 0. It never blocks.
15
19
  * The heuristic is deliberately loose (inject on any change-intent verb,
16
20
  * stay quiet on obvious reads) -- a spurious reminder is cheap; a missed one
@@ -36,6 +36,52 @@ auto, `acceptEdits` or `bypassPermissions` mode overrides a spoke's
36
36
  guards bound a spoke, not `permissionMode`. Source:
37
37
  [sub-agents](https://code.claude.com/docs/en/sub-agents).
38
38
 
39
+ ## Guard limits and overrides (detail)
40
+
41
+ Sources: [hooks](https://code.claude.com/docs/en/hooks),
42
+ [hooks guide](https://code.claude.com/docs/en/hooks-guide),
43
+ [managed settings](https://code.claude.com/docs/en/managed-settings),
44
+ [mods events](https://code.claude.com/docs/en/plugins/mods/events),
45
+ [sub-agents](https://code.claude.com/docs/en/sub-agents) and
46
+ [agent teams](https://code.claude.com/docs/en/agent-teams).
47
+
48
+ - **The `Bash` screen is conservative.** `guard-hub-src-writes.mjs` blocks
49
+ redirects, `tee`, `sed -i`, `cp`/`mv` into a guarded path, an interpreter
50
+ snippet that writes there, and a copy, move or removal of a parent
51
+ (`rsync -a /tmp/x/ ./`, `rm -rf .`). It cannot see an interpreter running a
52
+ script from a project file, an `eval`, a computed path, a parent of the
53
+ project root (`rm -rf ..`), a workspace container below the project root, a
54
+ build step, a formatter or fixer (`prettier --write`, `eslint --fix`),
55
+ `git rm`/`git mv`, `find -exec`, `xargs` with a computed operand,
56
+ `tar`/`curl -o`, or a very long interpreter call (allowed with a stderr
57
+ note).
58
+ - **Managed settings outrank every project file.** A `managed-settings.json`
59
+ file, an MDM policy or a console-managed policy has no project-level
60
+ override, and `allowManagedHooksOnly` and `allowManagedPermissionRulesOnly`
61
+ mean only managed hooks run and only managed permission rules apply. The
62
+ file lives outside any working tree, so nothing here can detect it. On a
63
+ machine you don't control, run `/status` and read its "Setting sources"
64
+ line: if `guard-hub-src-writes.mjs` and `guard-branch-isolation.mjs` aren't
65
+ 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`.
71
+ - **Who counts as a writer.** The guard needs a writer-spoke `agent_type` and a
72
+ non-empty `agent_id`. A fork subagent (on by default in every surface since
73
+ Claude Code 2.1.302) is not a writer spoke, so unless its payload reports a
74
+ 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
76
+ teammate has a documented `agent_id`; one built from a writer definition that
77
+ also reports that `agent_type` passes as a writer. A split-pane teammate does
78
+ not get `disallowedTools` (only an in-process one does), so every spoke's
79
+ `tools` list also omits `Agent`.
80
+ - **What `onFailure: "block"` covers.** A failure is a hook that cannot start,
81
+ times out, exits with any code other than 0 or 2, or prints invalid JSON. It
82
+ has no effect on `Stop`, `SubagentStop`, `TaskCompleted`, `TeammateIdle` or
83
+ async hooks.
84
+
39
85
  ## Dispatch sizing
40
86
 
41
87
  - **Decompose before you dispatch.** Scale the dispatch to task complexity —
@@ -87,73 +87,54 @@ Skills, each in `.claude/skills/<name>/`:
87
87
  sweeps (see Freshness).
88
88
 
89
89
  **The guard also screens `Bash`, but only conservatively.** The same hook
90
- runs on every `Bash` call and blocks a command that visibly writes into
91
- `src/` or `tests/` (redirects, `tee`, `sed -i`, `cp`/`mv` into them, a
92
- `python`/`node`/`php` snippet that writes or deletes there, a copy, move or
93
- removal of a parent of `src/` such as `rsync -a /tmp/x/ ./` or `rm -rf .`, and
94
- similar) unless the caller is `test-author` or `code-implementer`. It cannot
95
- catch an indirect write -- an interpreter running a script from a project
96
- file, an `eval`, a computed path, a parent of the project root (`rm -rf ..`), a workspace container below the project root (`tools/packages/foo`), a build step, a formatter or fixer
97
- (`prettier --write`, `eslint --fix`), `git rm`/`git mv`, `find -exec`, `xargs` with a computed operand, `tar`/`curl -o`, a very long
98
- interpreter call (allowed with a stderr note) -- so hub-and-spoke remains a convention backed by a guard that raises the bar,
99
- not a proof. To override it deliberately, run the command yourself with the
100
- `!` prefix at the Claude Code prompt, or edit the hook's registration in
101
- `.claude/settings.json`.
102
-
103
- **A Claude Code Enterprise/managed deployment sits above this and can
104
- silently disable it.** Managed settings (a `managed-settings.json` file, an
105
- MDM policy, or a claude.ai-console-managed remote policy) take precedence
106
- over every file this baseline installs, with no project-level override, and
107
- two managed-only keys -- `allowManagedHooksOnly` and
108
- `allowManagedPermissionRulesOnly` -- mean that only managed hooks run
109
- (`allowManagedHooksOnly`) and only managed permission rules apply
110
- (`allowManagedPermissionRulesOnly`) (see
111
- [Claude Code's managed-settings docs](https://code.claude.com/docs/en/managed-settings)).
112
- Nothing in this project can detect or gate against that from inside the
113
- repo -- the managed file lives outside any working tree, at an OS-level
114
- path. Run `/status` on a machine you don't control before trusting
115
- `guard-hub-src-writes.mjs`/`guard-branch-isolation.mjs`: its "Setting
116
- sources" line names every active source, and if these hooks aren't among
117
- what's actually running, treat hub-and-spoke as an unenforced checklist
118
- until confirmed otherwise.
119
-
120
- **An installed Claude Code mod is a second silent override, below managed
121
- settings.** Per the
122
- [hooks guide](https://code.claude.com/docs/en/hooks-guide), a mod that
123
- handles `tool.check` "can approve a call that your `PreToolUse` hook blocked,
124
- unless the hook is in managed settings", and project `PreToolUse` hooks run
125
- only after the last mod calls `next` (see the
126
- [mods events reference](https://code.claude.com/docs/en/plugins/mods/events)).
127
- Only managed-settings hooks outrank a mod, and nothing in the repo can detect
128
- one. Check `/plugin` for installed mods alongside `/status`.
90
+ blocks a `Bash` command that visibly writes into `src/` or `tests/` (redirects,
91
+ `tee`, `sed -i`, `cp`/`mv` into them, an interpreter snippet that writes there,
92
+ a copy, move or removal of a parent of `src/` such as `rm -rf .`) unless the caller is
93
+ `test-author` or `code-implementer`. It cannot catch an indirect write (a
94
+ script from a project file, an `eval`, a computed path, a build step, a
95
+ formatter or fixer, `git rm`/`git mv`, `tar`/`curl -o`), so hub-and-spoke is a
96
+ convention backed by a guard that raises the bar, not a proof. To override it
97
+ deliberately, run the command yourself with the `!` prefix at the Claude Code
98
+ prompt, or edit the hook's registration in `.claude/settings.json`.
99
+
100
+ **Managed settings and mods can silently disable the guards.** A managed
101
+ deployment (`managed-settings.json`, MDM, a console policy) outranks every file
102
+ here, and `allowManagedHooksOnly` runs only managed hooks. An installed mod
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
105
+ either: on a machine you don't control, check `/status` ("Setting sources") and
106
+ `/plugin` before trusting `guard-hub-src-writes.mjs` and
107
+ `guard-branch-isolation.mjs`. Detail and sources:
108
+ `.claude/rules/agent-dispatch.md`.
129
109
 
130
110
  **The guard keys on `agent_id` as well as `agent_type`.** A call counts as a
131
- writer spoke only with both present, so a call carrying `agent_type` but no
132
- `agent_id` is treated as the hub and is blocked.
133
-
134
- **Four guards block when they crash, and a secrets deny rule ships in
111
+ writer spoke only with both present, so one carrying `agent_type` alone is
112
+ treated as the hub and blocked, as is a fork subagent unless its payload
113
+ reports a writer `agent_type` with an `agent_id` (details and versions in
114
+ `.claude/rules/agent-dispatch.md`). An in-process
115
+ agent-teams teammate has a documented `agent_id`, so one built from a writer
116
+ definition that reports that `agent_type` would pass.
117
+
118
+ **Four guards block when they fail, and a secrets deny rule ships in
135
119
  `settings.json`.** `guard-secret-writes`, `guard-hub-src-writes`,
136
120
  `guard-branch-isolation` and `guard-protected-paths` carry
137
- `"onFailure": "block"` (Claude Code 2.1.295 or later). By default a hook that
138
- crashes or times out lets the call through; with this key it is blocked. It
139
- applies only to a failure the hook does not handle itself: each guard still
140
- catches bad input and exits 0 on purpose, so the key covers a load error, a
141
- missing `node` or the 30-second timeout. Because `guard-hub-src-writes` is also
142
- registered on `Bash`, a missing `node` or a timed-out scan blocks every `Bash`
143
- call until it is fixed (run the command yourself with the `!` prefix to get
144
- past it). The style guards and `guard-git-push-signed` stay fail-open on
145
- purpose: the push guard has its own command parser and the remote's
146
- signed-commit rule is the authoritative layer. `permissions.deny` blocks
147
- `Read(./.env)`, `Read(./.env.*)` and `Read(./secrets/**)`, which also covers
148
- `cat`, `head` and `tail` on those files in `Bash`. It does not cover `grep -r`
149
- or a script that opens the file itself, and nothing else in this baseline does.
121
+ `"onFailure": "block"` (Claude Code 2.1.295 or later): a hook that cannot
122
+ start, times out, exits with any code other than 0 or 2, or prints invalid
123
+ JSON blocks the call instead of letting it through. Each guard still handles
124
+ bad input itself and exits 0 on purpose. Because `guard-hub-src-writes` is also
125
+ on `Bash`, a missing `node` blocks every `Bash` call until fixed (run the
126
+ command with the `!` prefix to get past it). The style guards and
127
+ `guard-git-push-signed` stay fail-open on purpose: the push guard has its own
128
+ parser and the remote's signed-commit rule is the authoritative layer.
129
+ `permissions.deny` blocks `Read(./.env)`, `Read(./.env.*)` and
130
+ `Read(./secrets/**)`, which also covers `cat`, `head` and `tail` on them in
131
+ `Bash`. It does not cover `grep -r` or a script that opens the file itself.
150
132
 
151
133
  **A spoke's `permissionMode` can be overridden.** A session in auto,
152
134
  `acceptEdits` or `bypassPermissions` mode overrides a spoke's `permissionMode`
153
- (the field applies only when the session is in `default`, `dontAsk` or
154
- `plan`), so treat the hooks, not `permissionMode`, as what bounds a spoke.
155
- Claude Code also lets a subagent spawn subagents three layers deep by default;
156
- `disallowedTools: Agent` on every spoke is what keeps this roster flat.
135
+ (the field applies only in `default`, `dontAsk` or `plan`), so the hooks, not
136
+ `permissionMode`, bound a spoke. A subagent can spawn subagents three layers
137
+ deep by default; `disallowedTools: Agent` on every spoke keeps the roster flat.
157
138
 
158
139
  Full dispatch-sizing and recovery guidance: `.claude/rules/agent-dispatch.md`
159
140
  (auto-loads when editing `.claude/skills/**` or `.claude/agents/**`).
@@ -12,7 +12,9 @@
12
12
  * types. Skips cleanly (exit 0, one warning) when the target has no
13
13
  * `exports` field -- a project that isn't published doesn't need this gate,
14
14
  * and `/customize` removes the step entirely for non-library project kinds
15
- * rather than leaving a permanently-skipped one behind.
15
+ * rather than leaving a permanently-skipped one behind. attw resolves types
16
+ * with the TypeScript it bundles, not the project's own, so its verdict
17
+ * follows that resolver.
16
18
  */
17
19
  import process from "node:process";
18
20
  import { execFileSync } from "node:child_process";
@@ -691,7 +691,7 @@ const descriptionSubstance = {
691
691
  } else if (description.length > DESCRIPTION_MAX) {
692
692
  failures.push({
693
693
  subject,
694
- message: `description is ${description.length} chars; over ${DESCRIPTION_MAX} it is truncated in the skill listing`,
694
+ message: `description is ${description.length} chars; over the ${DESCRIPTION_MAX}-char Agent Skills maximum (Claude Code also truncates description + when_to_use at 1,536 in its skill listing)`,
695
695
  });
696
696
  }
697
697
  };
@@ -65,6 +65,8 @@ export default defineConfig(
65
65
  "@typescript-eslint/no-non-null-assertion": "error",
66
66
  "@typescript-eslint/no-floating-promises": "error",
67
67
  "@typescript-eslint/switch-exhaustiveness-check": "error",
68
+ // Overlaps `verbatimModuleSyntax` (typescript-eslint warns the two can
69
+ // report the same import twice); kept for the rule's autofix.
68
70
  "@typescript-eslint/consistent-type-imports": "error",
69
71
  "@typescript-eslint/no-unused-vars": [
70
72
  "error",
@@ -19,9 +19,10 @@ export default defineConfig({
19
19
  // barrel pattern): a fresh scaffold's index.ts IS its real content,
20
20
  // so excluding it would make this gate measure nothing at all.
21
21
  exclude: ["**/*.d.ts"],
22
- // json emits coverage-final.json: the v8 text table hides files that
23
- // are 100% on every metric, so the JSON is the authoritative
24
- // per-file record when investigating a suspected gap.
22
+ // json emits coverage-final.json: the text table can hide files that
23
+ // are 100% on every metric (Vitest sets `skipFull` when it detects an
24
+ // AI coding agent), so the JSON is the authoritative per-file record
25
+ // when investigating a suspected gap.
25
26
  reporter: ["text", "html", "json"],
26
27
  thresholds: {
27
28
  // Scaffold-appropriate starting floor. Raise these to the project's
@@ -105,9 +105,12 @@ already enumerate groups rather than individual steps.
105
105
 
106
106
  | Pack | Contents |
107
107
  | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
108
- | `harness-extras` | Claude Code session ergonomics: the compaction-handoff hook pair, a read-only Bash guard, and a five-row status line (session, model, context, quota, work) plus a per-subagent row renderer. The only pack that sets top-level settings keys (`statusLine`, `subagentStatusLine`). |
108
+ | `harness-extras` | Claude Code session hooks: the compaction-handoff hook pair (`PreCompact`, `SessionStart`) and a read-only Bash guard for review spokes. Registers hooks only; no top-level settings keys. |
109
+ | `statusline` | A five-row `statusLine` (session, model, context, quota, work) plus a per-subagent row renderer. The only pack that sets top-level settings keys (`statusLine`, `subagentStatusLine`); a project that already defines either must decide on it, see its `adoptNotes`. |
109
110
  | `quality` | Two language-level review aids: a per-file size ratchet gate (`check-file-budget.mjs`, a `build`-group verify step) and a read-only `type-design-analyzer` agent. No hooks, no settings. Adopt-capable and recommended for every project kind. |
110
- | `github` | GitHub-hosted collaboration: Anthropic's official Claude Code GitHub Action wired for `@claude` mention-mode, a second Action that posts an automated Claude review comment on every PR, and three `gh`-CLI skills — `reviewing-dependabot-prs`, `triaging-scan-alerts`, `watching-pr-checks`. No hooks, no gate. The two workflows need an auth secret this pack cannot create; see its `adoptNotes`. |
111
- | `publishing` | A release pipeline: `release.yml` (changesets version-PR / staged, provenance-attested npm publish via trusted publishing), `check-publish-version.mjs`, `check-dts-deps.mjs`, `check-license-headers.mjs` and a `REUSE.toml` template. Fresh mode only; see "The wiring contract" above and its `adoptNotes`. |
111
+ | `claude-github` | Anthropic's official Claude Code GitHub Action: one workflow wired for `@claude` mention-mode and a second that posts an automated Claude review comment on every PR. A pure file drop: no hooks, no gate. The workflows need an auth secret this pack cannot create and the review spends API credits per PR; see its `adoptNotes`. |
112
+ | `github` | GitHub-hosted collaboration through the `gh` CLI: three skills — `reviewing-dependabot-prs`, `triaging-scan-alerts`, `watching-pr-checks`. No hooks, no gate, no workflows. `triaging-scan-alerts` needs code scanning turned on; see its `adoptNotes`. |
113
+ | `publishing` | A release pipeline: `release.yml` (changesets version-PR / staged, provenance-attested npm publish via trusted publishing), `check-publish-version.mjs` and `check-dts-deps.mjs`. Fresh mode only; see "The wiring contract" above and its `adoptNotes`. |
114
+ | `licensing` | An SPDX/REUSE license-header gate: `check-license-headers.mjs` (a `lint`-group verify step) and a `REUSE.toml` template. Fresh mode only: the one-time backfill (`setupSteps`) fails an established project's `pnpm verify` until it has touched every file; see its `adoptNotes`. |
112
115
  | `supply-chain` | Secret scanning (`gitleaks.yml` with a `.gitleaks.toml`) and an OpenSSF Scorecard run (`scorecard.yml`) for any project on GitHub, published or not. A pure file drop of two workflows (read-only apart from the Scorecard job's `security-events` and `id-token` write): no hooks, no settings, no scripts, no gate. Adopt-capable and recommended for every project kind. |
113
116
  | `worktrees` | Enforces that all src/tests development happens inside an isolated git worktree, on any branch, for any caller: a `working-in-worktrees` skill (start/status/sync/finish/fan-out), a `SessionStart` hook that installs dependencies into a freshly created worktree, a `PreToolUse` guard stricter than the baseline's own `guard-branch-isolation.mjs`/`guard-hub-src-writes.mjs`, a `repair-core-bare.mjs` hook (`SessionStart`, and `PostToolUse` after `EnterWorktree`/`ExitWorktree`/`Agent`) that resets the `core.bare = true` Claude Code's worktree tools are reported to leave in a normal repo's shared config, and a `.worktreeinclude` copying `.env`/`.env.local`/`.env.*.local` into every worktree Claude Code creates. Changes the day-to-day workflow, not just a nicety — see its `adoptNotes`. |
@@ -86,7 +86,7 @@ jobs:
86
86
  fetch-depth: 0
87
87
 
88
88
  - id: claude
89
- uses: anthropics/claude-code-action@6fed3ca145920b639991cb756090506e1bcaf515 # v1.0.245
89
+ uses: anthropics/claude-code-action@5eb090f3c3afd701a0672cd32981197ca27688f6 # v1.0.253
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@6fed3ca145920b639991cb756090506e1bcaf515 # v1.0.245
70
+ uses: anthropics/claude-code-action@5eb090f3c3afd701a0672cd32981197ca27688f6 # v1.0.253
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
@@ -0,0 +1,19 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "name": "claude-github",
4
+ "description": "Anthropic's official Claude Code GitHub Action (anthropics/claude-code-action) on top of the baseline, as two workflows: claude.yml, wired for @claude mention-mode, and claude-pr-review.yml, which posts an automated Claude review comment on every pull request. Pure file drop: no hooks, no settings, no scripts, no verify step. Both need an auth secret this pack cannot create, and the review workflow spends API credits on every PR, so it is a separate pack from `github` rather than a default.",
5
+ "modes": ["fresh", "adopt"],
6
+ "budget": {
7
+ "agents": 0,
8
+ "skills": 0,
9
+ "hooks": 0,
10
+ "workflows": 2,
11
+ "scripts": 0
12
+ },
13
+ "wiring": {
14
+ "settings": {},
15
+ "packageScripts": {},
16
+ "verifySteps": []
17
+ },
18
+ "adoptNotes": "claude.yml only reacts to @claude mentions from a repository owner, member or collaborator (author_association), so an outside commenter on a public repository cannot start a job that holds contents: write and your auth secret. It also commits through the GitHub API (use_commit_signing) so a signed-commits ruleset accepts its work. claude-pr-review.yml runs on every non-bot, non-fork pull request, so it spends API credits on each push -- delete it and keep claude.yml if you only want on-demand help. Both workflows need one thing this pack cannot verify or install: an ANTHROPIC_API_KEY repository secret (the active default), or a CLAUDE_CODE_OAUTH_TOKEN from a Claude subscription, or a Workload Identity Federation setup in the Anthropic Console -- see the comments in .github/workflows/claude.yml for all three. An adopted project that already has its own .github/workflows/claude.yml or claude-pr-review.yml surfaces as an ordinary file conflict -- keep the existing one if it's already configured for that project's own auth choice, since this pack's version would just overwrite a working setup with its own generic defaults. The two workflows ship without an SPDX header on purpose (a header would carry a project-name token that stays literal in an adopt-mode install); a project that also installs `licensing` gets the headers from that pack's `check-license-headers.mjs --fix` backfill. These workflows used to ship inside the `github` pack; a project that installed that pack before the split keeps its files untouched."
19
+ }
@@ -1,13 +1,13 @@
1
1
  {
2
2
  "schemaVersion": 1,
3
3
  "name": "github",
4
- "description": "GitHub-hosted collaboration on top of the baseline: Anthropic's official Claude Code GitHub Action (anthropics/claude-code-action) wired for @claude mention-mode, a second Action that posts an automated Claude review comment on every PR, and three gh-CLI skills -- reviewing-dependabot-prs (classify and batch-merge open Dependabot PRs), triaging-scan-alerts (triage open code-scanning alerts to file:line, report only), and watching-pr-checks (check a PR's CI status and hand off to a project's own /triaging-ci on a real failure).",
4
+ "description": "GitHub-hosted collaboration skills on top of the baseline, all driven by the gh CLI: reviewing-dependabot-prs (classify and batch-merge open Dependabot PRs), triaging-scan-alerts (triage open code-scanning alerts to file:line, report only), and watching-pr-checks (check a PR's CI status and hand off to a project's own /triaging-ci on a real failure). No hooks, no gate, no workflows: the Claude Code GitHub Action workflows are the separate `claude-github` pack.",
5
5
  "modes": ["fresh", "adopt"],
6
6
  "budget": {
7
7
  "agents": 0,
8
8
  "skills": 3,
9
9
  "hooks": 0,
10
- "workflows": 2,
10
+ "workflows": 0,
11
11
  "scripts": 0
12
12
  },
13
13
  "wiring": {
@@ -15,5 +15,5 @@
15
15
  "packageScripts": {},
16
16
  "verifySteps": []
17
17
  },
18
- "adoptNotes": "claude.yml only reacts to @claude mentions from a repository owner, member or collaborator (author_association), so an outside commenter on a public repository cannot start a job that holds contents: write and your auth secret. It also commits through the GitHub API (use_commit_signing) so a signed-commits ruleset accepts its work. Both workflows need one thing this pack cannot verify or install: an ANTHROPIC_API_KEY repository secret (the active default), or a CLAUDE_CODE_OAUTH_TOKEN from a Claude subscription, or a Workload Identity Federation setup in the Anthropic Console -- see the comments in .github/workflows/claude.yml for all three. An adopted project that already has its own .github/workflows/claude.yml or claude-pr-review.yml surfaces as an ordinary file conflict -- keep the existing one if it's already configured for that project's own auth choice, since this pack's version would just overwrite a working setup with its own generic defaults. triaging-scan-alerts reads code-scanning alerts, and nothing in the baseline or this pack produces them: turn on GitHub's CodeQL default setup for the repository (Settings > Code security), or install the `supply-chain` pack, whose scorecard.yml uploads SARIF, otherwise the skill's first call returns \"code scanning is not enabled\" and reports nothing. The other two skills have no such dependency: they install anywhere a .claude/ directory exists and need only `gh` CLI auth (already required by every other gh-CLI-based skill this baseline ships). watching-pr-checks' handoff to /triaging-ci degrades gracefully if the project doesn't have that skill installed -- it still reports the real failure, just without the handoff."
18
+ "adoptNotes": "The three skills need only `gh` CLI auth (already required by every other gh-CLI-based skill this baseline ships) and install anywhere a .claude/ directory exists. triaging-scan-alerts reads code-scanning alerts, and nothing in the baseline or this pack produces them: turn on GitHub's CodeQL default setup for the repository (Settings > Code security), or install the `supply-chain` pack, whose scorecard.yml uploads SARIF, otherwise the skill's first call returns \"code scanning is not enabled\" and reports nothing. watching-pr-checks' handoff to /triaging-ci degrades gracefully if the project doesn't have that skill installed -- it still reports the real failure, just without the handoff. The Claude Code GitHub Action workflows (claude.yml, claude-pr-review.yml) used to ship in this pack and are now the separate `claude-github` pack; a project that installed this pack before the split keeps those files untouched."
19
19
  }
@@ -1,12 +1,12 @@
1
1
  {
2
2
  "schemaVersion": 1,
3
3
  "name": "harness-extras",
4
- "description": "Adds Claude Code session ergonomics on top of the baseline: a pair of hooks that carry a work summary across a context-window compaction, a hook that blocks non-read-only Bash commands from read-only review spokes, and a five-row statusLine (plus a per-subagent row renderer) -- the only documented surface carrying live context-window pressure.",
4
+ "description": "Adds Claude Code session ergonomics on top of the baseline: a pair of hooks that carry a work summary across a context-window compaction, and a hook that blocks non-read-only Bash commands from read-only review spokes. The status line is the separate `statusline` pack.",
5
5
  "modes": ["fresh", "adopt"],
6
6
  "budget": {
7
7
  "agents": 0,
8
8
  "skills": 0,
9
- "hooks": 6,
9
+ "hooks": 3,
10
10
  "workflows": 0,
11
11
  "scripts": 0
12
12
  },
@@ -51,20 +51,8 @@
51
51
  }
52
52
  ]
53
53
  },
54
- "settingsTopLevel": {
55
- "statusLine": {
56
- "type": "command",
57
- "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/statusline.mjs\"",
58
- "refreshInterval": 30,
59
- "padding": 1
60
- },
61
- "subagentStatusLine": {
62
- "type": "command",
63
- "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/subagent-statusline.mjs\""
64
- }
65
- },
66
54
  "packageScripts": {},
67
55
  "verifySteps": []
68
56
  },
69
- "adoptNotes": "The statusline and compaction hooks install anywhere a .claude/ directory exists, but guard-readonly-bash.mjs imports ../../bin/lib/agent-roster.mjs (the baseline's list of writer spokes) -- copy that file alongside it in an adopted project, or skip that one hook. The PreCompact hook writes tmp/compact-handoff-<session_id>.json under the git worktree the session runs in (from the hook payload's cwd, since CLAUDE_PROJECT_DIR does not follow a session into a linked worktree) -- fresh mode's baseline .gitignore already lists tmp/ unconditionally, but an adopted project's own .gitignore was never touched by adopt mode, so add tmp/ there too before this pack's hooks run, or the handoff artifact can end up committed. The statusline scripts read only the stdin payload, .git/HEAD (via node:fs, never a git subprocess) and process.availableMemory()/os.totalmem(), so they install anywhere a .claude/ directory exists -- no dependency on the baseline's file layout. The one real adopt risk is the two top-level settings keys: a project that already defines statusLine or subagentStatusLine collides, and its existing value must be shown and decided on, never overwritten -- if either is already set, skip that key and the three statusline scripts, and install the rest of this pack (the hooks) normally rather than failing the whole install. A statusLine in .claude/settings.local.json (or one passed with --settings) also shadows the project one; the user's own ~/.claude/settings.json ranks lower and does not -- check those before concluding the pack is wired. rate_limits.spend_limit and prompt_cache need Claude Code v2.1.251+, and the per-subagent model/contextWindowSize/effort fields need v2.1.205+/v2.1.214+, and the agentType label a row falls back to when a subagent has no name needs v2.1.293+; each renders only when present, so an older Claude Code degrades to fewer segments rather than breaking. The scripts behave the same on macOS and Linux; the memory segment uses process.availableMemory() (Node 22+), and on macOS with an older Node it is hidden rather than shown from os.freemem(), which undercounts there. Below roughly 40 columns the layout drops segments by priority rather than wrapping. The size-ratchet gate and the type-design-analyzer agent that used to ship here are now the separate `quality` pack."
57
+ "adoptNotes": "The compaction hooks install anywhere a .claude/ directory exists, but guard-readonly-bash.mjs imports ../../bin/lib/agent-roster.mjs (the baseline's list of writer spokes) -- copy that file alongside it in an adopted project, or skip that one hook. The PreCompact hook writes tmp/compact-handoff-<session_id>.json under the git worktree the session runs in (from the hook payload's cwd, since CLAUDE_PROJECT_DIR does not follow a session into a linked worktree) -- fresh mode's baseline .gitignore already lists tmp/ unconditionally, but an adopted project's own .gitignore was never touched by adopt mode, so add tmp/ there too before this pack's hooks run, or the handoff artifact can end up committed. The size-ratchet gate and the type-design-analyzer agent that used to ship here are now the separate `quality` pack. The status line that used to ship here is now the separate `statusline` pack, so installing this one never touches a project's own `statusLine` setting."
70
58
  }
@@ -0,0 +1,31 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "name": "licensing",
4
+ "description": "An SPDX/REUSE license-header gate for a new project: check-license-headers.mjs (a lint-group verify step that fails on any git-tracked file with neither an SPDX header nor a REUSE.toml annotation, and inserts missing headers with --fix) and a REUSE.toml template. Fresh mode only, because the one-time backfill fails an established project's pnpm verify until it has touched every file. Split from `publishing` so a project can take the header gate without the npm release pipeline, and the other way round.",
5
+ "modes": ["fresh"],
6
+ "budget": {
7
+ "agents": 0,
8
+ "skills": 0,
9
+ "hooks": 0,
10
+ "workflows": 0,
11
+ "scripts": 0
12
+ },
13
+ "wiring": {
14
+ "settings": {},
15
+ "packageScripts": {},
16
+ "verifySteps": [
17
+ {
18
+ "id": "license-headers",
19
+ "group": "lint",
20
+ "name": "Check SPDX license headers",
21
+ "cmd": ["node", "bin/check-license-headers.mjs"]
22
+ }
23
+ ]
24
+ },
25
+ "setupSteps": [
26
+ "git add -A",
27
+ "node bin/check-license-headers.mjs --fix",
28
+ "git add -A"
29
+ ],
30
+ "adoptNotes": "REQUIRED right after install, before the first pnpm verify: `git add -A`, then `node bin/check-license-headers.mjs --fix`, then `git add -A` again and commit the result (the gate only checks git-tracked files, so a fresh project with nothing staged passes it vacuously and fails on every file at its first push) -- templates/core has never had a license-header gate before this pack, so every one of its own files (hooks, bin/ scripts, CI workflows, the placeholder src/tests, and the workflows of any other installed pack such as `claude-github` or `supply-chain`) is missing the SPDX header this pack's gate now requires. The shipped REUSE.toml and gate header use NOASSERTION as the license identifier because the pack cannot know the project's license: edit REUSE.toml and the headerLines() function in bin/check-license-headers.mjs once it is decided (a LICENSE file, if one exists, is the source of truth). In a hand-copied install the CLI does not substitute tokens, so replace every literal `__PROJECT_NAME__` in the copied files (REUSE.toml, the SPDX headers) with the project's real name first. Fresh mode only: the backfill fails an established project's pnpm verify until it has touched every file, so it is staged like every other pack (at .groundwork/packs/licensing/) but never auto-installed in adopt mode -- if an adopted project wants it, copy .groundwork/packs/licensing/files/ by hand, dropping the `.staged` suffix from every name (or copy templates/packs/licensing/files/ from this repo directly) and run the backfill above. The license-headers verify step is a lint-group gate and installs anywhere a bin/verify.mjs-shaped gate runner exists; wire it into the project's real one if it differs. REUSE.toml also carries globs for `.gitleaks.toml` and `.worktreeinclude`, the files the `supply-chain` and `worktrees` packs add, so the gate's uncovered-file check passes whether or not those packs are installed. This gate used to ship in the `publishing` pack; a project that installed that pack before the split keeps its files untouched."
31
+ }