create-agentic-pdlc 2.2.1 → 2.3.0

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.
Files changed (33) hide show
  1. package/.agentic-pdlc/SETUP_PROMPT.md +3 -4
  2. package/.agentic-pdlc/metrics/raw/2026-W18.jsonl +2 -0
  3. package/.agentic-pdlc/metrics/raw/2026-W21.jsonl +68 -0
  4. package/.agentic-pdlc/templates/.github/workflows/agent-trigger.yml +2 -2
  5. package/.agentic-pdlc/templates/.github/workflows/agentic-metrics.yml +16 -9
  6. package/.agentic-pdlc/templates/.github/workflows/ci.yml +14 -0
  7. package/.agentic-pdlc/templates/.github/workflows/pdlc-health-check.yml +0 -2
  8. package/.agentic-pdlc/templates/.github/workflows/project-automation.yml +1 -5
  9. package/.agentic-pdlc/templates/.github/workflows/qa-agent.yml +4 -4
  10. package/.agentic-pdlc/templates/AGENTS.md +24 -1
  11. package/.agentic-pdlc/templates/docs/pdlc.md +21 -13
  12. package/.agentic-setup-prompt.md +3 -4
  13. package/.agentic-setup.md +3 -4
  14. package/.github/workflows/agentic-metrics.yml +21 -11
  15. package/.github/workflows/pdlc-health-check.yml +0 -2
  16. package/.github/workflows/project-automation.yml +31 -7
  17. package/.github/workflows/qa-agent.yml +4 -4
  18. package/AGENTS.md +1 -1
  19. package/CLAUDE.md +51 -3
  20. package/SETUP.md +2 -0
  21. package/adapters/claude-code/skill.md +13 -10
  22. package/adapters/hooks/pdlc-stage-gate.sh +3 -3
  23. package/bin/cli.js +18 -7
  24. package/docs/flow.md +8 -21
  25. package/docs/pdlc.md +21 -13
  26. package/package.json +1 -1
  27. package/templates/.github/workflows/agent-trigger.yml +2 -2
  28. package/templates/.github/workflows/ci.yml +14 -0
  29. package/templates/.github/workflows/pdlc-health-check.yml +0 -2
  30. package/templates/.github/workflows/project-automation.yml +24 -6
  31. package/templates/.github/workflows/qa-agent.yml +6 -4
  32. package/templates/AGENTS.md +25 -2
  33. package/templates/docs/pdlc.md +21 -13
@@ -25,10 +25,10 @@ If any of these files are missing, you are in **Setup Mode**. Do not proceed wit
25
25
  - **Project basics:** Project Name, Description, Technical Stack (Structure), and GitHub Username (for CODEOWNERS security).
26
26
  - **Commands:** Test command, Lint command, Build command.
27
27
  - **Invariants:** Critical business rules agents must never violate (e.g. Human-in-the-loop).
28
- - **Board IDs:** PROJECT_ID, STATUS_FIELD_ID, column option IDs (provide standard PDLC options: Idea, Exploration, Brainstorming, Detail Solution, Approval, Development, Testing, Code Review / PR, Production). Allow user to answer "skip", which means you leave the placeholders intact.
28
+ - **Board IDs:** PROJECT_ID, STATUS_FIELD_ID, column option IDs (provide standard PDLC options: Idea, Brainstorming, Detail Solution, Approval, Development, Testing, Code Review / PR, Production). Allow user to answer "skip", which means you leave the placeholders intact.
29
29
  - **Architecture Violation:** Ask "Does your project use an automated architecture auditing tool (e.g., a CI job that creates issues with an `architecture-violation` label)?". If yes, uncomment the `move-violation-to-board` job inside `project-automation.yml`. If no, ask if they would like help implementing one, reminding them that it significantly improves their agentic development process. If they decline, you can leave the job commented out.
30
30
  - **QA Agent (Variant B):** Ask "Do you plan to use an AI QA Agent (e.g. QAWolf or a secondary script) to verify your PRs before Code Review?". If yes, explain you will adopt Variant B: you will change `STATUS_CODE_REVIEW_PR` to `STATUS_TESTING` inside the `move-card-on-pr-open` job in `project-automation.yml` and uncomment the `move-card-on-qa-pass` job. If no, leave the workflow as Variant A (default) and delete the optional `.github/workflows/qa-agent.yml` template.
31
- - **Implementation agent handle:** e.g., `@google-labs-jules`, or "none".
31
+ - **Implementation agent handle:** e.g., `@google-labs-jules`, or "none". When replacing `{{IMPLEMENTATION_AGENT_LABEL}}` in `agent-trigger.yml`: for Jules use `jules` (the native label the Jules GitHub App watches — **not** `agent:jules`); for other agents use the handle without `@`, lowercase.
32
32
  3. Generate and write the missing files replacing the `{{SCREAMING_SNAKE_CASE}}` placeholders using the templates logic you know (usually they reside in standard Agentic PDLC templates).
33
33
  4. Offer to run the `gh` commands for labels (`spec:approved`, `pr:in-review`, `pr:approved`, `architecture-violation`).
34
34
  5. Commit everything with the message: `chore: setup agentic-pdlc framework`.
@@ -68,6 +68,5 @@ Do not write code for downstream features! Your goal is to refine the Spec, so t
68
68
 
69
69
  ### 4. Moving the Board (Upstream States)
70
70
  As you actively work with the user advancing the feature, you MUST use the GitHub CLI to update internal state labels. This triggers GitHub Actions behind the scenes.
71
- - Starting context evaluation: Run `gh issue edit <N> --add-label "stage:exploration"`
72
- - Presenting architecture/approaches: Run `gh issue edit <N> --add-label "stage:brainstorming"`
71
+ - Starting work on an issue (before reading code): Run `gh issue edit <N> --add-label "stage:brainstorming"`
73
72
  - Starting to write the technical spec: Run `gh issue edit <N> --add-label "stage:detailing"`
@@ -0,0 +1,2 @@
1
+ {"issueNumber": 5, "stage": "stage:exploration", "durationDays": 3.0}
2
+ {"issueNumber": 5, "stage": "stage:detailing", "durationDays": 1.5}
@@ -0,0 +1,68 @@
1
+ {"issueNumber":66,"stage":"stage:development","durationDays":5}
2
+ {"issueNumber":66,"stage":"stage:approval","durationDays":0}
3
+ {"issueNumber":67,"stage":"stage:brainstorming","durationDays":0}
4
+ {"issueNumber":67,"stage":"stage:detailing","durationDays":0}
5
+ {"issueNumber":67,"stage":"stage:approval","durationDays":0}
6
+ {"issueNumber":74,"stage":"stage:detailing","durationDays":0}
7
+ {"issueNumber":74,"stage":"stage:approval","durationDays":0}
8
+ {"issueNumber":75,"stage":"stage:detailing","durationDays":0}
9
+ {"issueNumber":75,"stage":"stage:approval","durationDays":0}
10
+ {"issueNumber":76,"stage":"stage:detailing","durationDays":0}
11
+ {"issueNumber":76,"stage":"stage:approval","durationDays":0}
12
+ {"issueNumber":78,"stage":"stage:detailing","durationDays":0}
13
+ {"issueNumber":78,"stage":"stage:approval","durationDays":0}
14
+ {"issueNumber":80,"stage":"stage:detailing","durationDays":0}
15
+ {"issueNumber":80,"stage":"stage:approval","durationDays":0}
16
+ {"issueNumber":80,"stage":"stage:development","durationDays":3.1}
17
+ {"issueNumber":84,"stage":"stage:brainstorming","durationDays":0}
18
+ {"issueNumber":84,"stage":"stage:detailing","durationDays":0}
19
+ {"issueNumber":84,"stage":"stage:approval","durationDays":0}
20
+ {"issueNumber":84,"stage":"stage:development","durationDays":0}
21
+ {"issueNumber":85,"stage":"stage:brainstorming","durationDays":0}
22
+ {"issueNumber":85,"stage":"stage:detailing","durationDays":0}
23
+ {"issueNumber":85,"stage":"stage:approval","durationDays":0}
24
+ {"issueNumber":85,"stage":"stage:approval","durationDays":0}
25
+ {"issueNumber":87,"stage":"stage:approval","durationDays":0}
26
+ {"issueNumber":87,"stage":"stage:development","durationDays":0}
27
+ {"issueNumber":87,"stage":"stage:brainstorming","durationDays":0}
28
+ {"issueNumber":87,"stage":"stage:detailing","durationDays":0}
29
+ {"issueNumber":87,"stage":"stage:approval","durationDays":0}
30
+ {"issueNumber":88,"stage":"stage:brainstorming","durationDays":0}
31
+ {"issueNumber":88,"stage":"stage:detailing","durationDays":0}
32
+ {"issueNumber":88,"stage":"stage:approval","durationDays":0}
33
+ {"issueNumber":88,"stage":"stage:development","durationDays":0}
34
+ {"issueNumber":89,"stage":"stage:brainstorming","durationDays":0}
35
+ {"issueNumber":90,"stage":"stage:brainstorming","durationDays":0}
36
+ {"issueNumber":90,"stage":"stage:detailing","durationDays":0}
37
+ {"issueNumber":90,"stage":"stage:approval","durationDays":0}
38
+ {"issueNumber":90,"stage":"stage:approval","durationDays":0}
39
+ {"issueNumber":91,"stage":"stage:brainstorming","durationDays":0}
40
+ {"issueNumber":91,"stage":"stage:detailing","durationDays":0}
41
+ {"issueNumber":91,"stage":"stage:approval","durationDays":0}
42
+ {"issueNumber":91,"stage":"stage:development","durationDays":0}
43
+ {"issueNumber":92,"stage":"stage:brainstorming","durationDays":0}
44
+ {"issueNumber":92,"stage":"stage:detailing","durationDays":0}
45
+ {"issueNumber":92,"stage":"stage:approval","durationDays":0}
46
+ {"issueNumber":92,"stage":"stage:development","durationDays":0}
47
+ {"issueNumber":93,"stage":"stage:brainstorming","durationDays":0}
48
+ {"issueNumber":93,"stage":"stage:detailing","durationDays":0}
49
+ {"issueNumber":93,"stage":"stage:approval","durationDays":0}
50
+ {"issueNumber":93,"stage":"stage:development","durationDays":0}
51
+ {"issueNumber":94,"stage":"stage:brainstorming","durationDays":0}
52
+ {"issueNumber":94,"stage":"stage:detailing","durationDays":0}
53
+ {"issueNumber":94,"stage":"stage:approval","durationDays":0}
54
+ {"issueNumber":96,"stage":"stage:brainstorming","durationDays":0}
55
+ {"issueNumber":96,"stage":"stage:detailing","durationDays":0}
56
+ {"issueNumber":96,"stage":"stage:approval","durationDays":0}
57
+ {"issueNumber":96,"stage":"stage:development","durationDays":0}
58
+ {"issueNumber":97,"stage":"stage:brainstorming","durationDays":0}
59
+ {"issueNumber":97,"stage":"stage:detailing","durationDays":0}
60
+ {"issueNumber":97,"stage":"stage:approval","durationDays":0}
61
+ {"issueNumber":109,"stage":"stage:brainstorming","durationDays":0}
62
+ {"issueNumber":109,"stage":"stage:detailing","durationDays":0}
63
+ {"issueNumber":109,"stage":"stage:approval","durationDays":0}
64
+ {"issueNumber":109,"stage":"stage:development","durationDays":0}
65
+ {"issueNumber":113,"stage":"stage:brainstorming","durationDays":0}
66
+ {"issueNumber":113,"stage":"stage:detailing","durationDays":0}
67
+ {"issueNumber":113,"stage":"stage:approval","durationDays":0}
68
+ {"issueNumber":113,"stage":"stage:development","durationDays":0}
@@ -75,7 +75,7 @@ jobs:
75
75
  console.log(`Issue #${number} → Development`);
76
76
 
77
77
  - name: Comment on issue to trigger agent and prevent race conditions
78
- if: ${{ !contains('{{IMPLEMENTATION_AGENT_LABEL}}', '{{') }}
78
+ if: ${{ !contains('{{IMPLEMENTATION_AGENT_LABEL}}', '{{') && vars.JULES_ENABLED == 'true' }}
79
79
  uses: actions/github-script@v7
80
80
  with:
81
81
  github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -118,7 +118,7 @@ jobs:
118
118
  contents: read
119
119
  steps:
120
120
  - name: Comment on issue to trigger agent
121
- if: ${{ !contains('{{IMPLEMENTATION_AGENT_LABEL}}', '{{') }}
121
+ if: ${{ !contains('{{IMPLEMENTATION_AGENT_LABEL}}', '{{') && vars.JULES_ENABLED == 'true' }}
122
122
  uses: actions/github-script@v7
123
123
  with:
124
124
  github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -25,7 +25,7 @@ jobs:
25
25
  const { owner, repo } = context.repo;
26
26
  const since = new Date(Date.now() - 7 * 24 * 60 * 60 * 1000).toISOString();
27
27
  const STAGE_LABELS = new Set([
28
- 'stage:exploration', 'stage:brainstorming', 'stage:detailing',
28
+ 'stage:brainstorming', 'stage:detailing',
29
29
  'stage:approval', 'stage:development', 'stage:testing'
30
30
  ]);
31
31
 
@@ -297,7 +297,6 @@ jobs:
297
297
  const records = fs.readFileSync(jsonlPath, 'utf8').trim().split('\n').filter(Boolean).map(JSON.parse);
298
298
  if (records.length > 0) {
299
299
  const STAGES = [
300
- ['stage:exploration', 'Exploration'],
301
300
  ['stage:brainstorming', 'Brainstorming'],
302
301
  ['stage:detailing', 'Detailing'],
303
302
  ['stage:approval', 'Approval'],
@@ -394,19 +393,27 @@ jobs:
394
393
  console.log(`Created label ${LABEL}`);
395
394
  }
396
395
 
397
- // Close previous pulse issues
396
+ // Close previous pulse issues; upsert if same week already exists
398
397
  const prev = await github.rest.issues.listForRepo({
399
398
  owner, repo, labels: LABEL, state: 'open', per_page: 20
400
399
  });
400
+ let existingIssue = null;
401
401
  for (const issue of prev.data) {
402
- if (issue.title !== title) {
402
+ if (issue.title === title) {
403
+ existingIssue = issue;
404
+ console.log(`Found existing pulse for ${title}: #${issue.number} — will update body`);
405
+ } else {
403
406
  await github.rest.issues.update({ owner, repo, issue_number: issue.number, state: 'closed' });
404
407
  console.log(`Closed previous pulse: #${issue.number}`);
405
408
  }
406
409
  }
407
410
 
408
- // Create new pulse issue
409
- const created = await github.rest.issues.create({
410
- owner, repo, title, body, labels: [LABEL]
411
- });
412
- console.log(`✅ Created pulse issue: #${created.data.number} — ${title}`);
411
+ if (existingIssue) {
412
+ await github.rest.issues.update({ owner, repo, issue_number: existingIssue.number, body });
413
+ console.log(`✅ Updated pulse issue: #${existingIssue.number} — ${title}`);
414
+ } else {
415
+ const created = await github.rest.issues.create({
416
+ owner, repo, title, body, labels: [LABEL]
417
+ });
418
+ console.log(`✅ Created pulse issue: #${created.data.number} — ${title}`);
419
+ }
@@ -38,3 +38,17 @@ jobs:
38
38
  if: ${{ !contains('{{TEST_COMMAND}}', '{{') }}
39
39
  run: |
40
40
  {{TEST_COMMAND}}
41
+
42
+ ci-status:
43
+ name: Sentinel / CI
44
+ needs: [validate]
45
+ if: always()
46
+ runs-on: ubuntu-latest
47
+ steps:
48
+ - name: Check validate result
49
+ run: |
50
+ result="${{ needs.validate.result }}"
51
+ if [[ "$result" != "success" && "$result" != "skipped" ]]; then
52
+ echo "CI failed: validate=$result"
53
+ exit 1
54
+ fi
@@ -8,7 +8,6 @@ on:
8
8
  env:
9
9
  PROJECT_ID: "{{PROJECT_ID}}"
10
10
  STATUS_FIELD_ID: "{{STATUS_FIELD_ID}}"
11
- STATUS_EXPLORATION: "{{ID_EXPLORATION}}"
12
11
  STATUS_BRAINSTORMING: "{{ID_BRAINSTORMING}}"
13
12
  STATUS_DETAILING: "{{ID_DETAILING}}"
14
13
  STATUS_APPROVAL: "{{ID_APPROVAL}}"
@@ -35,7 +34,6 @@ jobs:
35
34
  const projectId = process.env.PROJECT_ID;
36
35
  const statusFieldId = process.env.STATUS_FIELD_ID;
37
36
  const envVars = {
38
- 'STATUS_EXPLORATION': process.env.STATUS_EXPLORATION,
39
37
  'STATUS_BRAINSTORMING': process.env.STATUS_BRAINSTORMING,
40
38
  'STATUS_DETAILING': process.env.STATUS_DETAILING,
41
39
  'STATUS_APPROVAL': process.env.STATUS_APPROVAL,
@@ -12,7 +12,6 @@ env:
12
12
  PROJECT_ID: "{{PROJECT_ID}}"
13
13
  STATUS_FIELD_ID: "{{STATUS_FIELD_ID}}"
14
14
  STATUS_IDEA: "{{ID_IDEA}}"
15
- STATUS_EXPLORATION: "{{ID_EXPLORATION}}"
16
15
  STATUS_BRAINSTORMING: "{{ID_BRAINSTORMING}}"
17
16
  STATUS_DETAILING: "{{ID_DETAILING}}"
18
17
  STATUS_APPROVAL: "{{ID_APPROVAL}}"
@@ -40,10 +39,7 @@ jobs:
40
39
  let targetStatusId = null;
41
40
  let stageName = null;
42
41
 
43
- if (labelName === 'stage:exploration') {
44
- targetStatusId = process.env.STATUS_EXPLORATION;
45
- stageName = 'Exploration';
46
- } else if (labelName === 'stage:brainstorming') {
42
+ if (labelName === 'stage:brainstorming') {
47
43
  targetStatusId = process.env.STATUS_BRAINSTORMING;
48
44
  stageName = 'Brainstorming';
49
45
  } else if (labelName === 'stage:detailing') {
@@ -64,7 +64,7 @@ jobs:
64
64
  --max-time 30 || echo "API_ERROR")
65
65
 
66
66
  if [ "$RESPONSE" = "API_ERROR" ]; then
67
- gh pr edit "$PR_NUMBER" --add-label "infra:qa-broken"
67
+ GH_TOKEN="$PROJECT_PAT" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=infra:qa-broken'
68
68
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** Could not reach GitHub Models API. Manual review required."
69
69
  exit 0
70
70
  fi
@@ -73,13 +73,13 @@ jobs:
73
73
  EXPLANATION=$(echo "$RESPONSE" | python3 -c 'import json,sys; d=json.load(sys.stdin); t=d.get("choices",[{}])[0].get("message",{}).get("content","").strip(); lines=t.split("\n",1); print(lines[1].strip() if len(lines)>1 else "")')
74
74
 
75
75
  if echo "$VERDICT" | grep -q "^PASS"; then
76
- gh pr edit "$PR_NUMBER" --add-label "qa:approved"
76
+ GH_TOKEN="$PROJECT_PAT" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=qa:approved'
77
77
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** AC coverage verified. ${EXPLANATION}"
78
78
  elif echo "$VERDICT" | grep -q "^FAIL"; then
79
- gh pr edit "$PR_NUMBER" --add-label "qa:needs-work"
79
+ GH_TOKEN="$PROJECT_PAT" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=qa:needs-work'
80
80
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** AC coverage insufficient. ${EXPLANATION}"
81
81
  else
82
- gh pr edit "$PR_NUMBER" --add-label "infra:qa-broken"
82
+ GH_TOKEN="$PROJECT_PAT" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=infra:qa-broken'
83
83
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** Could not parse GitHub Models response. Manual review required."
84
84
  fi
85
85
 
@@ -30,7 +30,7 @@ Always start from the current `main` HEAD. Never work over stale snapshots.
30
30
  ## Mandatory Workflow
31
31
 
32
32
  0. **Identity**: Always prefix your GitHub comments with `🤖 **Agent:** ` to distinguish yourself.
33
- 1. **Initial State**: When beginning work on a new issue, your very first action must be to apply the `stage:exploration` label using the GitHub CLI (`gh issue edit <N> --add-label "stage:exploration"`).
33
+ 1. **Initial State**: When beginning work on a new issue, your very first action must be to apply the `stage:brainstorming` label using the GitHub CLI (`gh issue edit <N> --add-label "stage:brainstorming"`).
34
34
  2. Read the issue entirely — understand its type (US/BUG/TASK/SPIKE) and the Acceptance Criteria.
35
35
  3. Read `docs/pdlc.md` — understand the PDLC and the Definition of Done in this project.
36
36
  4. Read all files mentioned in the issue's technical context.
@@ -64,12 +64,35 @@ When detailing a solution in an issue body, you must **always** include both the
64
64
  - `path/to/file.ts` — what changes
65
65
  ```
66
66
 
67
+ ## Stage Transition Rules (non-negotiable)
68
+
69
+ MUST apply `stage:brainstorming` label immediately on starting work — before reading
70
+ any code, before invoking any skill. Then read context and present problem summary
71
+ + 2–3 solution options in a single message.
72
+
73
+ MUST NOT add `stage:detailing` label until the user has explicitly selected
74
+ an approach in the current conversation turn. Work done in a prior
75
+ planning session does NOT count as confirmation.
76
+
77
+ MUST NOT add `spec:approved`, `stage:development`, or manually add
78
+ `stage:approval` — these represent final human approval or the result of it.
79
+ `stage:approval` is only set by system automation after you provide a complete
80
+ spec for human review. Adding them manually triggers irreversible automation
81
+ (Jules dispatch, board move).
82
+
83
+ Each stage transition requires a fresh explicit signal from the user in the same
84
+ session where the transition happens. These rules have no exceptions.
85
+
67
86
  ## What NOT to do
68
87
 
69
88
  - Never commit directly to `main`.
70
89
  - Never open a PR without passing the tests.
71
90
  - Never implement beyond the immediate scope of the issue.
72
91
  - Never create future-proofing abstractions for hypothetical features.
92
+ - The agent MUST NOT apply these labels under any circumstances (PM only):
93
+ - `spec:approved`: triggers Jules dispatch + board move to Development.
94
+ - `qa:approved`: triggers board move to Code Review.
95
+ - `qa:needs-work`: signals the PR requires changes and halts the flow.
73
96
  {{EXTRA_DONT}}
74
97
 
75
98
  ## Project Standards
@@ -4,9 +4,8 @@
4
4
 
5
5
  | Column | Meaning | Who moves the card |
6
6
  |---|---|---|
7
- | 💡 Idea — don't move manually to Exploration | Backlog — tell agent: "work on issue #XX" | Don't move manually |
8
- | 🔍 Exploration | Claude is analyzing code and context | Label `stage:exploration` |
9
- | 🧠 Brainstorming | Claude proposed approaches, awaiting PM gate | Label `stage:brainstorming` |
7
+ | 💡 Idea | Backlog — tell agent: "work on issue #XX" | Don't move manually |
8
+ | 🧠 Brainstorming | AI reading context, proposing approaches and trade-offs | Label `stage:brainstorming` |
10
9
  | 📐 Detail Solution | Claude is writing the technical spec | Label `stage:detailing` |
11
10
  | ✅ Approval | Spec ready, awaiting `spec:approved` label | Label `spec:approved` |
12
11
  | ⚙️ Development | Agent implementing the spec | Label `stage:development` |
@@ -37,7 +36,6 @@ REPO = {{REPO_OWNER}}/{{REPO_NAME}}
37
36
  | Column | Option ID |
38
37
  |---|---|
39
38
  | 💡 Idea | `{{ID_IDEA}}` |
40
- | 🔍 Exploration | `{{ID_EXPLORATION}}` |
41
39
  | 🧠 Brainstorming | `{{ID_BRAINSTORMING}}` |
42
40
  | 📐 Detail Solution | `{{ID_DETAIL}}` |
43
41
  | ✅ Approval | `{{ID_APPROVAL}}` |
@@ -70,7 +68,6 @@ REPO = {{REPO_OWNER}}/{{REPO_NAME}}
70
68
 
71
69
  | Label | Entity | Color | Meaning |
72
70
  |---|---|---|---|
73
- | `stage:exploration` | Issue | Purple | Issue is being evaluated |
74
71
  | `stage:brainstorming` | Issue | Pink | Proposed approaches awaiting PM gate |
75
72
  | `stage:detailing` | Issue | Blue | Technical spec is being written |
76
73
  | `stage:development` | Issue | Orange | Agent is implementing the spec |
@@ -78,15 +75,15 @@ REPO = {{REPO_OWNER}}/{{REPO_NAME}}
78
75
  | `pr:in-review` | PR | Yellow | Awaiting code review |
79
76
  | `pr:approved` | PR | Green | Code review approved |
80
77
  | `type:us` | Issue | Blue | New feature or behavioral change — full flow |
81
- | `type:task` | Issue | Yellow | Operational/non-functional change — skips brainstorming |
82
- | `type:bug` | Issue | Red | Something broken — skips brainstorming |
78
+ | `type:task` | Issue | Yellow | Operational/non-functional change — full flow |
79
+ | `type:bug` | Issue | Red | Something broken — full flow |
83
80
  | `type:spike` | Issue | Gray | Research/evaluation — never reaches Development |
84
81
 
85
82
  ## Approval Gates
86
83
 
87
84
  **Gate 1 — PM/Ideation (Brainstorming):**
88
- You comment on the issue approving one of the approaches proposed by the ideation agent.
89
- Format: *"Approved — proceed with option X."*
85
+ Agent presents problem summary + 2–3 solution options in a single message. You select an approach.
86
+ Format: *"Option X"* or *"Go with B"* or *"Approved — proceed with option X."*
90
87
 
91
88
  **Gate 2 — Tech Lead (Spec):**
92
89
  You add the `spec:approved` label to the issue after reviewing the technical spec in the body.
@@ -98,13 +95,24 @@ The `type:*` label is the authoritative signal — set automatically by the agen
98
95
 
99
96
  | Label | Flow |
100
97
  |---|---|
101
- | `type:us` | Full flow — exploration → brainstorming → Gate 1 → detailing → approval |
102
- | `type:task` | Skips brainstorming exploration → detailing → approval |
103
- | `type:bug` | Skips brainstorming exploration → detailing → approval |
104
- | `type:spike` | Skips brainstorming exploration → detailing → conclusion comment (never reaches Development) |
98
+ | `type:us` | brainstorming → Gate 1 → detailing → approval |
99
+ | `type:task` | brainstorming Gate 1 → detailing → approval |
100
+ | `type:bug` | brainstorming Gate 1 → detailing → approval |
101
+ | `type:spike` | brainstorming Gate 1 → detailing → conclusion comment (never reaches Development) |
105
102
 
106
103
  If no `type:*` label present and agent confidence < 85%, defaults to `type:us` (safe fallback — never skips gates by omission).
107
104
 
105
+ ## Bypass Mechanism
106
+
107
+ Agents MUST NOT skip any stage. The ONLY authorized bypasses are:
108
+
109
+ | Mechanism | Who authorizes | What it bypasses |
110
+ |---|---|---|
111
+ | `human-approved` label on issue | PM (human) only | All stage gates |
112
+ | Branch prefix `hotfix/` | PM (human) only | PR gate only |
113
+
114
+ Agents MUST NOT self-authorize a bypass. Stop and ask the PM explicitly.
115
+
108
116
  ## Definition of Done
109
117
 
110
118
  An issue is truly done when:
@@ -25,10 +25,10 @@ If any of these files are missing, you are in **Setup Mode**. Do not proceed wit
25
25
  - **Project basics:** Project Name, Description, Technical Stack (Structure), and GitHub Username (for CODEOWNERS security).
26
26
  - **Commands:** Test command, Lint command, Build command.
27
27
  - **Invariants:** Critical business rules agents must never violate (e.g. Human-in-the-loop).
28
- - **Board IDs:** PROJECT_ID, STATUS_FIELD_ID, column option IDs (provide standard PDLC options: Idea, Exploration, Brainstorming, Detail Solution, Approval, Development, Testing, Code Review / PR, Production). Allow user to answer "skip", which means you leave the placeholders intact.
28
+ - **Board IDs:** PROJECT_ID, STATUS_FIELD_ID, column option IDs (provide standard PDLC options: Idea, Brainstorming, Detail Solution, Approval, Development, Testing, Code Review / PR, Production). Allow user to answer "skip", which means you leave the placeholders intact.
29
29
  - **Architecture Violation:** Ask "Does your project use an automated architecture auditing tool (e.g., a CI job that creates issues with an `architecture-violation` label)?". If yes, uncomment the `move-violation-to-board` job inside `project-automation.yml`. If no, ask if they would like help implementing one, reminding them that it significantly improves their agentic development process. If they decline, you can leave the job commented out.
30
30
  - **QA Agent (Variant B):** Ask "Do you plan to use an AI QA Agent (e.g. QAWolf or a secondary script) to verify your PRs before Code Review?". If yes, explain you will adopt Variant B: you will change `STATUS_CODE_REVIEW_PR` to `STATUS_TESTING` inside the `move-card-on-pr-open` job in `project-automation.yml` and uncomment the `move-card-on-qa-pass` job. If no, leave the workflow as Variant A (default) and delete the optional `.github/workflows/qa-agent.yml` template.
31
- - **Implementation agent handle:** e.g., `@google-labs-jules`, or "none".
31
+ - **Implementation agent handle:** e.g., `@google-labs-jules`, or "none". When replacing `{{IMPLEMENTATION_AGENT_LABEL}}` in `agent-trigger.yml`: for Jules use `jules` (the native label the Jules GitHub App watches — **not** `agent:jules`); for other agents use the handle without `@`, lowercase.
32
32
  3. Generate and write the missing files replacing the `{{SCREAMING_SNAKE_CASE}}` placeholders using the templates logic you know (usually they reside in standard Agentic PDLC templates).
33
33
  4. Offer to run the `gh` commands for labels (`spec:approved`, `pr:in-review`, `pr:approved`, `architecture-violation`).
34
34
  5. Commit everything with the message: `chore: setup agentic-pdlc framework`.
@@ -68,6 +68,5 @@ Do not write code for downstream features! Your goal is to refine the Spec, so t
68
68
 
69
69
  ### 4. Moving the Board (Upstream States)
70
70
  As you actively work with the user advancing the feature, you MUST use the GitHub CLI to update internal state labels. This triggers GitHub Actions behind the scenes.
71
- - Starting context evaluation: Run `gh issue edit <N> --add-label "stage:exploration"`
72
- - Presenting architecture/approaches: Run `gh issue edit <N> --add-label "stage:brainstorming"`
71
+ - Starting work on an issue (before reading code): Run `gh issue edit <N> --add-label "stage:brainstorming"`
73
72
  - Starting to write the technical spec: Run `gh issue edit <N> --add-label "stage:detailing"`
package/.agentic-setup.md CHANGED
@@ -25,10 +25,10 @@ If any of these files are missing, you are in **Setup Mode**. Do not proceed wit
25
25
  - **Project basics:** Project Name, Description, Technical Stack (Structure), and GitHub Username (for CODEOWNERS security).
26
26
  - **Commands:** Test command, Lint command, Build command.
27
27
  - **Invariants:** Critical business rules agents must never violate (e.g. Human-in-the-loop).
28
- - **Board IDs:** PROJECT_ID, STATUS_FIELD_ID, column option IDs (provide standard PDLC options: Idea, Exploration, Brainstorming, Detail Solution, Approval, Development, Testing, Code Review / PR, Production). Allow user to answer "skip", which means you leave the placeholders intact.
28
+ - **Board IDs:** PROJECT_ID, STATUS_FIELD_ID, column option IDs (provide standard PDLC options: Idea, Brainstorming, Detail Solution, Approval, Development, Testing, Code Review / PR, Production). Allow user to answer "skip", which means you leave the placeholders intact.
29
29
  - **Architecture Violation:** Ask "Does your project use an automated architecture auditing tool (e.g., a CI job that creates issues with an `architecture-violation` label)?". If yes, uncomment the `move-violation-to-board` job inside `project-automation.yml`. If no, ask if they would like help implementing one, reminding them that it significantly improves their agentic development process. If they decline, you can leave the job commented out.
30
30
  - **QA Agent (Variant B):** Ask "Do you plan to use an AI QA Agent (e.g. QAWolf or a secondary script) to verify your PRs before Code Review?". If yes, explain you will adopt Variant B: you will change `STATUS_CODE_REVIEW_PR` to `STATUS_TESTING` inside the `move-card-on-pr-open` job in `project-automation.yml` and uncomment the `move-card-on-qa-pass` job. If no, leave the workflow as Variant A (default) and delete the optional `.github/workflows/qa-agent.yml` template.
31
- - **Implementation agent handle:** e.g., `@google-labs-jules`, or "none".
31
+ - **Implementation agent handle:** e.g., `@google-labs-jules`, or "none". When replacing `{{IMPLEMENTATION_AGENT_LABEL}}` in `agent-trigger.yml`: for Jules use `jules` (the native label the Jules GitHub App watches — **not** `agent:jules`); for other agents use the handle without `@`, lowercase.
32
32
  3. Generate and write the missing files replacing the `{{SCREAMING_SNAKE_CASE}}` placeholders using the templates logic you know (usually they reside in standard Agentic PDLC templates).
33
33
  4. Offer to run the `gh` commands for labels (`spec:approved`, `pr:in-review`, `pr:approved`, `architecture-violation`).
34
34
  5. Commit everything with the message: `chore: setup agentic-pdlc framework`.
@@ -68,6 +68,5 @@ Do not write code for downstream features! Your goal is to refine the Spec, so t
68
68
 
69
69
  ### 4. Moving the Board (Upstream States)
70
70
  As you actively work with the user advancing the feature, you MUST use the GitHub CLI to update internal state labels. This triggers GitHub Actions behind the scenes.
71
- - Starting context evaluation: Run `gh issue edit <N> --add-label "stage:exploration"`
72
- - Presenting architecture/approaches: Run `gh issue edit <N> --add-label "stage:brainstorming"`
71
+ - Starting work on an issue (before reading code): Run `gh issue edit <N> --add-label "stage:brainstorming"`
73
72
  - Starting to write the technical spec: Run `gh issue edit <N> --add-label "stage:detailing"`
@@ -25,7 +25,7 @@ jobs:
25
25
  const { owner, repo } = context.repo;
26
26
  const since = new Date(Date.now() - 7 * 24 * 60 * 60 * 1000).toISOString();
27
27
  const STAGE_LABELS = new Set([
28
- 'stage:exploration', 'stage:brainstorming', 'stage:detailing',
28
+ 'stage:brainstorming', 'stage:detailing',
29
29
  'stage:approval', 'stage:development', 'stage:testing'
30
30
  ]);
31
31
 
@@ -297,7 +297,6 @@ jobs:
297
297
  const records = fs.readFileSync(jsonlPath, 'utf8').trim().split('\n').filter(Boolean).map(JSON.parse);
298
298
  if (records.length > 0) {
299
299
  const STAGES = [
300
- ['stage:exploration', 'Exploration'],
301
300
  ['stage:brainstorming', 'Brainstorming'],
302
301
  ['stage:detailing', 'Detailing'],
303
302
  ['stage:approval', 'Approval'],
@@ -311,11 +310,14 @@ jobs:
311
310
  }
312
311
  const avg = arr => arr.reduce((a, b) => a + b, 0) / arr.length;
313
312
 
314
- let maxStage = null, maxDays = 0;
313
+ let maxStage = null, maxDays = -1;
315
314
  const rows = [];
316
315
  for (const [stage, label] of STAGES) {
317
316
  const days = byStage[stage];
318
- if (!days) continue;
317
+ if (!days) {
318
+ rows.push(`| **${label}** | — | — |`);
319
+ continue;
320
+ }
319
321
  const a = round1(avg(days));
320
322
  rows.push(`| **${label}** | ${a}d | ${days.length} |`);
321
323
  if (a > maxDays) { maxStage = label; maxDays = a; }
@@ -394,19 +396,27 @@ jobs:
394
396
  console.log(`Created label ${LABEL}`);
395
397
  }
396
398
 
397
- // Close previous pulse issues
399
+ // Close previous pulse issues; upsert if same week already exists
398
400
  const prev = await github.rest.issues.listForRepo({
399
401
  owner, repo, labels: LABEL, state: 'open', per_page: 20
400
402
  });
403
+ let existingIssue = null;
401
404
  for (const issue of prev.data) {
402
- if (issue.title !== title) {
405
+ if (issue.title === title) {
406
+ existingIssue = issue;
407
+ console.log(`Found existing pulse for ${title}: #${issue.number} — will update body`);
408
+ } else {
403
409
  await github.rest.issues.update({ owner, repo, issue_number: issue.number, state: 'closed' });
404
410
  console.log(`Closed previous pulse: #${issue.number}`);
405
411
  }
406
412
  }
407
413
 
408
- // Create new pulse issue
409
- const created = await github.rest.issues.create({
410
- owner, repo, title, body, labels: [LABEL]
411
- });
412
- console.log(`✅ Created pulse issue: #${created.data.number} — ${title}`);
414
+ if (existingIssue) {
415
+ await github.rest.issues.update({ owner, repo, issue_number: existingIssue.number, body });
416
+ console.log(`✅ Updated pulse issue: #${existingIssue.number} — ${title}`);
417
+ } else {
418
+ const created = await github.rest.issues.create({
419
+ owner, repo, title, body, labels: [LABEL]
420
+ });
421
+ console.log(`✅ Created pulse issue: #${created.data.number} — ${title}`);
422
+ }
@@ -8,7 +8,6 @@ on:
8
8
  env:
9
9
  PROJECT_ID: "PVT_kwHODpFFL84BXg7h"
10
10
  STATUS_FIELD_ID: "PVTSSF_lAHODpFFL84BXg7hzhStRHI"
11
- STATUS_EXPLORATION: "96ac537d"
12
11
  STATUS_BRAINSTORMING: "8eb07c5b"
13
12
  STATUS_DETAILING: "9f6ce70e"
14
13
  STATUS_APPROVAL: "31bf4610"
@@ -35,7 +34,6 @@ jobs:
35
34
  const projectId = process.env.PROJECT_ID;
36
35
  const statusFieldId = process.env.STATUS_FIELD_ID;
37
36
  const envVars = {
38
- 'STATUS_EXPLORATION': process.env.STATUS_EXPLORATION,
39
37
  'STATUS_BRAINSTORMING': process.env.STATUS_BRAINSTORMING,
40
38
  'STATUS_DETAILING': process.env.STATUS_DETAILING,
41
39
  'STATUS_APPROVAL': process.env.STATUS_APPROVAL,
@@ -6,13 +6,12 @@ on:
6
6
  pull_request_review:
7
7
  types: [submitted]
8
8
  issues:
9
- types: [labeled]
9
+ types: [labeled, closed]
10
10
 
11
11
  env:
12
12
  PROJECT_ID: "PVT_kwHODpFFL84BXg7h"
13
13
  STATUS_FIELD_ID: "PVTSSF_lAHODpFFL84BXg7hzhStRHI"
14
14
  STATUS_IDEA: "bb6e5a20"
15
- STATUS_EXPLORATION: "96ac537d"
16
15
  STATUS_BRAINSTORMING: "8eb07c5b"
17
16
  STATUS_DETAILING: "9f6ce70e"
18
17
  STATUS_APPROVAL: "31bf4610"
@@ -40,10 +39,7 @@ jobs:
40
39
  let targetStatusId = null;
41
40
  let stageName = null;
42
41
 
43
- if (labelName === 'stage:exploration') {
44
- targetStatusId = process.env.STATUS_EXPLORATION;
45
- stageName = 'Exploration';
46
- } else if (labelName === 'stage:brainstorming') {
42
+ if (labelName === 'stage:brainstorming') {
47
43
  targetStatusId = process.env.STATUS_BRAINSTORMING;
48
44
  stageName = 'Brainstorming';
49
45
  } else if (labelName === 'stage:detailing') {
@@ -156,11 +152,17 @@ jobs:
156
152
  });
157
153
  };
158
154
 
155
+ const stageLabelsToRemove = ['stage:development', 'stage:brainstorming', 'stage:detailing', 'stage:approval', 'jules', 'agent:working'];
156
+
159
157
  if (linkedIssues.length > 0) {
160
158
  for (const n of linkedIssues) {
161
159
  const { data: issue } = await github.rest.issues.get({ owner, repo, issue_number: n });
162
160
  await moveItem(issue.node_id);
163
- console.log(`Issue #${n} Testing`);
161
+ for (const label of stageLabelsToRemove) {
162
+ await github.rest.issues.removeLabel({ owner, repo, issue_number: n, name: label }).catch(() => {});
163
+ }
164
+ await github.rest.issues.addLabels({ owner, repo, issue_number: n, labels: ['stage:testing'] }).catch(() => {});
165
+ console.log(`Issue #${n} → Testing (labels updated)`);
164
166
  }
165
167
  } else {
166
168
  await moveItem(pr.node_id);
@@ -282,3 +284,25 @@ jobs:
282
284
  } else {
283
285
  await moveItem(pr.node_id);
284
286
  }
287
+
288
+ cleanup-labels-on-close:
289
+ name: Issue closed → strip stage/agent labels
290
+ if: github.event_name == 'issues' && github.event.action == 'closed'
291
+ runs-on: ubuntu-latest
292
+ steps:
293
+ - name: Remove transient labels
294
+ uses: actions/github-script@v7
295
+ with:
296
+ github-token: ${{ secrets.GITHUB_TOKEN }}
297
+ script: |
298
+ const { owner, repo } = context.repo;
299
+ const issue_number = context.payload.issue.number;
300
+ const toRemove = [
301
+ 'stage:brainstorming', 'stage:detailing',
302
+ 'stage:approval', 'stage:development', 'stage:testing',
303
+ 'agent:working', 'qa:needs-work', 'pr:in-review', 'jules'
304
+ ];
305
+ for (const label of toRemove) {
306
+ await github.rest.issues.removeLabel({ owner, repo, issue_number, name: label }).catch(() => {});
307
+ }
308
+ console.log(`Issue #${issue_number} labels cleaned up`);
@@ -64,7 +64,7 @@ jobs:
64
64
  --max-time 30 || echo "API_ERROR")
65
65
 
66
66
  if [ "$RESPONSE" = "API_ERROR" ]; then
67
- gh pr edit "$PR_NUMBER" --add-label "infra:qa-broken"
67
+ GH_TOKEN="$PROJECT_TOKEN" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=infra:qa-broken'
68
68
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** Could not reach GitHub Models API. Manual review required."
69
69
  exit 0
70
70
  fi
@@ -73,13 +73,13 @@ jobs:
73
73
  EXPLANATION=$(echo "$RESPONSE" | python3 -c 'import json,sys; d=json.load(sys.stdin); t=d.get("choices",[{}])[0].get("message",{}).get("content","").strip(); lines=t.split("\n",1); print(lines[1].strip() if len(lines)>1 else "")')
74
74
 
75
75
  if echo "$VERDICT" | grep -q "^PASS"; then
76
- gh pr edit "$PR_NUMBER" --add-label "qa:approved"
76
+ GH_TOKEN="$PROJECT_TOKEN" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=qa:approved'
77
77
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** AC coverage verified. ${EXPLANATION}"
78
78
  elif echo "$VERDICT" | grep -q "^FAIL"; then
79
- gh pr edit "$PR_NUMBER" --add-label "qa:needs-work"
79
+ GH_TOKEN="$PROJECT_TOKEN" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=qa:needs-work'
80
80
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** AC coverage insufficient. ${EXPLANATION}"
81
81
  else
82
- gh pr edit "$PR_NUMBER" --add-label "infra:qa-broken"
82
+ GH_TOKEN="$PROJECT_TOKEN" gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/labels" --method POST -f 'labels[]=infra:qa-broken'
83
83
  gh pr comment "$PR_NUMBER" --body "🤖 **QA Agent:** Could not parse GitHub Models response. Manual review required."
84
84
  fi
85
85
 
package/AGENTS.md CHANGED
@@ -27,7 +27,7 @@ Always start from the current `main` HEAD. Never work over stale snapshots.
27
27
  ## Mandatory Workflow
28
28
 
29
29
  0. **Identity**: Always prefix your GitHub comments with `🤖 **Agent:** ` to distinguish yourself.
30
- 1. **Initial State**: When beginning work on a new issue, your very first action must be to apply the `stage:exploration` label using the GitHub CLI (`gh issue edit <N> --add-label "stage:exploration"`).
30
+ 1. **Initial State**: When beginning work on a new issue, your very first action must be to apply the `stage:brainstorming` label using the GitHub CLI (`gh issue edit <N> --add-label "stage:brainstorming"`).
31
31
  2. Read the issue entirely — understand its type (US/BUG/TASK/SPIKE) and the Acceptance Criteria.
32
32
  3. Read `docs/pdlc.md` — understand the PDLC and the Definition of Done in this project.
33
33
  4. Read all files mentioned in the issue's technical context.