@every-env/compound-plugin 2.39.0 → 2.40.0

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/CHANGELOG.md CHANGED
@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
7
7
 
8
8
  Release numbering now follows the repository `v*` tag line. Starting at `v2.34.0`, the root CLI package and this changelog stay on that shared version stream. Older entries below retain the previous `0.x` CLI numbering.
9
9
 
10
+ # [2.40.0](https://github.com/EveryInc/compound-engineering-plugin/compare/v2.39.0...v2.40.0) (2026-03-17)
11
+
12
+
13
+ ### Features
14
+
15
+ * specific model/harness/version in PR attribution ([#283](https://github.com/EveryInc/compound-engineering-plugin/issues/283)) ([fdbd584](https://github.com/EveryInc/compound-engineering-plugin/commit/fdbd584bac40ca373275b1b339ab81db65ac0958))
16
+
10
17
  # [2.39.0](https://github.com/EveryInc/compound-engineering-plugin/compare/v2.38.0...v2.39.0) (2026-03-16)
11
18
 
12
19
 
package/CLAUDE.md CHANGED
@@ -359,14 +359,27 @@ Follow these patterns for commit messages:
359
359
  - `Fix [issue]` - Bug fixes
360
360
  - `Simplify [component] to [improvement]` - Refactoring
361
361
 
362
- Include the Claude Code footer:
362
+ Include the attribution footer (fill in your actual values):
363
363
 
364
364
  ```
365
- 🤖 Generated with [Claude Code](https://claude.com/claude-code)
365
+ 🤖 Generated with [MODEL] via [HARNESS](HARNESS_URL) + Compound Engineering v[VERSION]
366
366
 
367
- Co-Authored-By: Claude <noreply@anthropic.com>
367
+ Co-Authored-By: [MODEL] ([CONTEXT] context, [THINKING]) <noreply@anthropic.com>
368
368
  ```
369
369
 
370
+ **Fill in at commit/PR time:**
371
+
372
+ | Placeholder | Value | Example |
373
+ |-------------|-------|---------|
374
+ | Placeholder | Value | Example |
375
+ |-------------|-------|---------|
376
+ | `[MODEL]` | Model name | Claude Opus 4.6, GPT-5.4 |
377
+ | `[CONTEXT]` | Context window (if known) | 200K, 1M |
378
+ | `[THINKING]` | Thinking level (if known) | extended thinking |
379
+ | `[HARNESS]` | Tool running you | Claude Code, Codex, Gemini CLI |
380
+ | `[HARNESS_URL]` | Link to that tool | `https://claude.com/claude-code` |
381
+ | `[VERSION]` | `plugin.json` → `version` | 2.40.0 |
382
+
370
383
  ## Resources to search for when needing more information
371
384
 
372
385
  - [Claude Code Plugin Documentation](https://docs.claude.com/en/docs/claude-code/plugins)
@@ -687,7 +687,7 @@ Use this checklist when adding a new target provider:
687
687
 
688
688
  ## Related Files
689
689
 
690
- - `/C:/Source/compound-engineering-plugin/.claude-plugin/plugin.json` — Version and component counts
691
- - `/C:/Source/compound-engineering-plugin/CHANGELOG.md` — Recent additions and patterns
692
- - `/C:/Source/compound-engineering-plugin/README.md` — Usage examples for all targets
693
- - `/C:/Source/compound-engineering-plugin/docs/solutions/plugin-versioning-requirements.md` — Checklist for releases
690
+ - `plugins/compound-engineering/.claude-plugin/plugin.json` — Version and component counts
691
+ - `CHANGELOG.md` — Recent additions and patterns
692
+ - `README.md` — Usage examples for all targets
693
+ - `docs/solutions/plugin-versioning-requirements.md` — Checklist for releases
@@ -72,8 +72,8 @@ This documentation serves as a reminder. When Claude Code works on this plugin,
72
72
 
73
73
  ## Related Files
74
74
 
75
- - `/Users/kieranklaassen/compound-engineering-plugin/plugins/compound-engineering/.claude-plugin/plugin.json`
76
- - `/Users/kieranklaassen/compound-engineering-plugin/plugins/compound-engineering/CHANGELOG.md`
77
- - `/Users/kieranklaassen/compound-engineering-plugin/plugins/compound-engineering/README.md`
78
- - `/Users/kieranklaassen/compound-engineering-plugin/package.json`
79
- - `/Users/kieranklaassen/compound-engineering-plugin/CHANGELOG.md`
75
+ - `plugins/compound-engineering/.claude-plugin/plugin.json`
76
+ - `plugins/compound-engineering/CHANGELOG.md`
77
+ - `plugins/compound-engineering/README.md`
78
+ - `package.json`
79
+ - `CHANGELOG.md`
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@every-env/compound-plugin",
3
- "version": "2.39.0",
3
+ "version": "2.40.0",
4
4
  "type": "module",
5
5
  "private": false,
6
6
  "bin": {
@@ -0,0 +1,110 @@
1
+ # Plugin Instructions
2
+
3
+ These instructions apply when working under `plugins/compound-engineering/`.
4
+ They supplement the repo-root `AGENTS.md`.
5
+
6
+ # Compounding Engineering Plugin Development
7
+
8
+ ## Versioning Requirements
9
+
10
+ **IMPORTANT**: Routine PRs should not cut releases for this plugin.
11
+
12
+ The repo uses an automatied release process to prepare plugin releases, including version selection and changelog generation. Because multiple PRs may merge before the next release, contributors cannot know the final released version from within an individual PR.
13
+
14
+ ### Contributor Rules
15
+
16
+ - Do **not** manually bump `.claude-plugin/plugin.json` version in a normal feature PR.
17
+ - Do **not** manually bump `.claude-plugin/marketplace.json` plugin version in a normal feature PR.
18
+ - Do **not** cut a release section in `CHANGELOG.md` for a normal feature PR.
19
+ - Do update substantive docs that are part of the actual change, such as `README.md`, component tables, usage instructions, or counts when they would otherwise become inaccurate.
20
+
21
+ ### Pre-Commit Checklist
22
+
23
+ Before committing ANY changes:
24
+
25
+ - [ ] No manual release-version bump in `.claude-plugin/plugin.json`
26
+ - [ ] No manual release-version bump in `.claude-plugin/marketplace.json`
27
+ - [ ] No manual release entry added to `CHANGELOG.md`
28
+ - [ ] README.md component counts verified
29
+ - [ ] README.md tables accurate (agents, commands, skills)
30
+ - [ ] plugin.json description matches current counts
31
+
32
+ ### Directory Structure
33
+
34
+ ```
35
+ agents/
36
+ ├── review/ # Code review agents
37
+ ├── research/ # Research and analysis agents
38
+ ├── design/ # Design and UI agents
39
+ └── docs/ # Documentation agents
40
+
41
+ skills/
42
+ ├── ce-*/ # Core workflow skills (ce:plan, ce:review, etc.)
43
+ ├── workflows-*/ # Deprecated aliases for ce:* skills
44
+ └── */ # All other skills
45
+ ```
46
+
47
+ > **Note:** Commands were migrated to skills in v2.39.0. All former
48
+ > `/command-name` slash commands now live under `skills/command-name/SKILL.md`
49
+ > and work identically in Claude Code. Other targets may convert or map these references differently.
50
+
51
+ ## Command Naming Convention
52
+
53
+ **Workflow commands** use `ce:` prefix to unambiguously identify them as compound-engineering commands:
54
+ - `/ce:brainstorm` - Explore requirements and approaches before planning
55
+ - `/ce:plan` - Create implementation plans
56
+ - `/ce:review` - Run comprehensive code reviews
57
+ - `/ce:work` - Execute work items systematically
58
+ - `/ce:compound` - Document solved problems
59
+
60
+ **Why `ce:`?** Claude Code has built-in `/plan` and `/review` commands. The `ce:` namespace (short for compound-engineering) makes it immediately clear these commands belong to this plugin. The legacy `workflows:` prefix is still supported as deprecated aliases that forward to the `ce:*` equivalents.
61
+
62
+ ## Skill Compliance Checklist
63
+
64
+ When adding or modifying skills, verify compliance with the skill spec:
65
+
66
+ ### YAML Frontmatter (Required)
67
+
68
+ - [ ] `name:` present and matches directory name (lowercase-with-hyphens)
69
+ - [ ] `description:` present and describes **what it does and when to use it** (per official spec: "Explains code with diagrams. Use when exploring how code works.")
70
+
71
+ ### Reference Links (Required if references/ exists)
72
+
73
+ - [ ] All files in `references/` are linked as `[filename.md](./references/filename.md)`
74
+ - [ ] All files in `assets/` are linked as `[filename](./assets/filename)`
75
+ - [ ] All files in `scripts/` are linked as `[filename](./scripts/filename)`
76
+ - [ ] No bare backtick references like `` `references/file.md` `` - use proper markdown links
77
+
78
+ ### Writing Style
79
+
80
+ - [ ] Use imperative/infinitive form (verb-first instructions)
81
+ - [ ] Avoid second person ("you should") - use objective language ("To accomplish X, do Y")
82
+
83
+ ### Cross-Platform User Interaction
84
+
85
+ - [ ] When a skill needs to ask the user a question, instruct use of the platform's blocking question tool and name the known equivalents (`AskUserQuestion` in Claude Code, `request_user_input` in Codex, `ask_user` in Gemini)
86
+ - [ ] Include a fallback for environments without a question tool (e.g., present numbered options and wait for the user's reply before proceeding)
87
+
88
+ ### Cross-Platform Reference Rules
89
+
90
+ This plugin is authored once, then converted for other agent platforms. Commands and agents are transformed during that conversion, but `plugin.skills` are usually copied almost exactly as written.
91
+
92
+ - [ ] Because of that, slash references inside command or agent content are acceptable when they point to real published commands; target-specific conversion can remap them.
93
+ - [ ] Inside a pass-through `SKILL.md`, do not assume slash references will be remapped for another platform. Write references according to what will still make sense after the skill is copied as-is.
94
+ - [ ] When one skill refers to another skill, prefer semantic wording such as "load the `document-review` skill" rather than slash syntax.
95
+ - [ ] Use slash syntax only when referring to an actual published command or workflow such as `/ce:work` or `/deepen-plan`.
96
+
97
+ ### Quick Validation Command
98
+
99
+ ```bash
100
+ # Check for unlinked references in a skill
101
+ grep -E '`(references|assets|scripts)/[^`]+`' skills/*/SKILL.md
102
+ # Should return nothing if all refs are properly linked
103
+
104
+ # Check description format - should describe what + when
105
+ grep -E '^description:' skills/*/SKILL.md
106
+ ```
107
+
108
+ ## Documentation
109
+
110
+ See `docs/solutions/plugin-versioning-requirements.md` for detailed versioning workflow.
@@ -1,97 +1 @@
1
- # Compounding Engineering Plugin Development
2
-
3
- ## Versioning Requirements
4
-
5
- **IMPORTANT**: Routine PRs should not cut releases for this plugin.
6
-
7
- The repo uses an automatied release process to prepare plugin releases, including version selection and changelog generation. Because multiple PRs may merge before the next release, contributors cannot know the final released version from within an individual PR.
8
-
9
- ### Contributor Rules
10
-
11
- - Do **not** manually bump `.claude-plugin/plugin.json` version in a normal feature PR.
12
- - Do **not** manually bump `.claude-plugin/marketplace.json` plugin version in a normal feature PR.
13
- - Do **not** cut a release section in `CHANGELOG.md` for a normal feature PR.
14
- - Do update substantive docs that are part of the actual change, such as `README.md`, component tables, usage instructions, or counts when they would otherwise become inaccurate.
15
-
16
- ### Pre-Commit Checklist
17
-
18
- Before committing ANY changes:
19
-
20
- - [ ] No manual release-version bump in `.claude-plugin/plugin.json`
21
- - [ ] No manual release-version bump in `.claude-plugin/marketplace.json`
22
- - [ ] No manual release entry added to `CHANGELOG.md`
23
- - [ ] README.md component counts verified
24
- - [ ] README.md tables accurate (agents, commands, skills)
25
- - [ ] plugin.json description matches current counts
26
-
27
- ### Directory Structure
28
-
29
- ```
30
- agents/
31
- ├── review/ # Code review agents
32
- ├── research/ # Research and analysis agents
33
- ├── design/ # Design and UI agents
34
- ├── workflow/ # Workflow automation agents
35
- └── docs/ # Documentation agents
36
-
37
- skills/
38
- ├── ce-*/ # Core workflow skills (ce:plan, ce:review, etc.)
39
- ├── workflows-*/ # Deprecated aliases for ce:* skills
40
- └── */ # All other skills
41
- ```
42
-
43
- > **Note:** Commands were migrated to skills in v2.39.0. All former
44
- > `/command-name` slash commands now live under `skills/command-name/SKILL.md`
45
- > and work identically (Claude Code 2.1.3+ merged the two formats).
46
-
47
- ## Command Naming Convention
48
-
49
- **Workflow commands** use `ce:` prefix to unambiguously identify them as compound-engineering commands:
50
- - `/ce:plan` - Create implementation plans
51
- - `/ce:review` - Run comprehensive code reviews
52
- - `/ce:work` - Execute work items systematically
53
- - `/ce:compound` - Document solved problems
54
- - `/ce:brainstorm` - Explore requirements and approaches before planning
55
-
56
- **Why `ce:`?** Claude Code has built-in `/plan` and `/review` commands. The `ce:` namespace (short for compound-engineering) makes it immediately clear these commands belong to this plugin. The legacy `workflows:` prefix is still supported as deprecated aliases that forward to the `ce:*` equivalents.
57
-
58
- ## Skill Compliance Checklist
59
-
60
- When adding or modifying skills, verify compliance with skill-creator spec:
61
-
62
- ### YAML Frontmatter (Required)
63
-
64
- - [ ] `name:` present and matches directory name (lowercase-with-hyphens)
65
- - [ ] `description:` present and describes **what it does and when to use it** (per official spec: "Explains code with diagrams. Use when exploring how code works.")
66
-
67
- ### Reference Links (Required if references/ exists)
68
-
69
- - [ ] All files in `references/` are linked as `[filename.md](./references/filename.md)`
70
- - [ ] All files in `assets/` are linked as `[filename](./assets/filename)`
71
- - [ ] All files in `scripts/` are linked as `[filename](./scripts/filename)`
72
- - [ ] No bare backtick references like `` `references/file.md` `` - use proper markdown links
73
-
74
- ### Writing Style
75
-
76
- - [ ] Use imperative/infinitive form (verb-first instructions)
77
- - [ ] Avoid second person ("you should") - use objective language ("To accomplish X, do Y")
78
-
79
- ### Cross-Platform User Interaction
80
-
81
- - [ ] When a skill needs to ask the user a question, instruct use of the platform's blocking question tool and name the known equivalents (`AskUserQuestion` in Claude Code, `request_user_input` in Codex, `ask_user` in Gemini)
82
- - [ ] Include a fallback for environments without a question tool (e.g., present numbered options and wait for the user's reply before proceeding)
83
-
84
- ### Quick Validation Command
85
-
86
- ```bash
87
- # Check for unlinked references in a skill
88
- grep -E '`(references|assets|scripts)/[^`]+`' skills/*/SKILL.md
89
- # Should return nothing if all refs are properly linked
90
-
91
- # Check description format - should describe what + when
92
- grep -E '^description:' skills/*/SKILL.md
93
- ```
94
-
95
- ## Documentation
96
-
97
- See `docs/solutions/plugin-versioning-requirements.md` for detailed versioning workflow.
1
+ @AGENTS.md
@@ -228,13 +228,28 @@ This command takes a work document (plan, specification, or todo file) and execu
228
228
 
229
229
  Brief explanation if needed.
230
230
 
231
- 🤖 Generated with [Claude Code](https://claude.com/claude-code)
231
+ 🤖 Generated with [MODEL] via [HARNESS](HARNESS_URL) + Compound Engineering v[VERSION]
232
232
 
233
- Co-Authored-By: Claude <noreply@anthropic.com>
233
+ Co-Authored-By: [MODEL] ([CONTEXT] context, [THINKING]) <noreply@anthropic.com>
234
234
  EOF
235
235
  )"
236
236
  ```
237
237
 
238
+ **Fill in at commit/PR time:**
239
+
240
+ | Placeholder | Value | Example |
241
+ |-------------|-------|---------|
242
+ | Placeholder | Value | Example |
243
+ |-------------|-------|---------|
244
+ | `[MODEL]` | Model name | Claude Opus 4.6, GPT-5.4 |
245
+ | `[CONTEXT]` | Context window (if known) | 200K, 1M |
246
+ | `[THINKING]` | Thinking level (if known) | extended thinking |
247
+ | `[HARNESS]` | Tool running you | Claude Code, Codex, Gemini CLI |
248
+ | `[HARNESS_URL]` | Link to that tool | `https://claude.com/claude-code` |
249
+ | `[VERSION]` | `plugin.json` → `version` | 2.40.0 |
250
+
251
+ Subagents creating commits/PRs are equally responsible for accurate attribution.
252
+
238
253
  2. **Capture and Upload Screenshots for UI Changes** (REQUIRED for any UI work)
239
254
 
240
255
  For **any** design changes, new views, or UI modifications, you MUST capture and upload screenshots:
@@ -308,7 +323,8 @@ This command takes a work document (plan, specification, or todo file) and execu
308
323
 
309
324
  ---
310
325
 
311
- [![Compound Engineered](https://img.shields.io/badge/Compound-Engineered-6366f1)](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with [Claude Code](https://claude.com/claude-code)
326
+ [![Compound Engineering v[VERSION]](https://img.shields.io/badge/Compound_Engineering-v[VERSION]-6366f1)](https://github.com/EveryInc/compound-engineering-plugin)
327
+ 🤖 Generated with [MODEL] ([CONTEXT] context, [THINKING]) via [HARNESS](HARNESS_URL)
312
328
  EOF
313
329
  )"
314
330
  ```
@@ -445,7 +461,7 @@ Before creating PR, verify:
445
461
  - [ ] Commit messages follow conventional format
446
462
  - [ ] PR description includes Post-Deploy Monitoring & Validation section (or explicit no-impact rationale)
447
463
  - [ ] PR description includes summary, testing notes, and screenshots
448
- - [ ] PR description includes Compound Engineered badge
464
+ - [ ] PR description includes Compound Engineered badge with accurate model, harness, and version
449
465
 
450
466
  ## When to Use Reviewer Agents
451
467