create-agdf 0.8.7 → 0.9.0

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 (58) hide show
  1. package/bin/create-agdf.js +67 -8
  2. package/generated/.github/skills/agdf-brownfield-analysis/SKILL.md +6 -2
  3. package/generated/.github/skills/agdf-clean-implementation-review/SKILL.md +9 -1
  4. package/generated/.github/skills/agdf-code-review/SKILL.md +9 -1
  5. package/generated/.github/skills/agdf-delivery-closeout/SKILL.md +5 -1
  6. package/generated/.github/skills/agdf-delivery-path-search/SKILL.md +5 -1
  7. package/generated/.github/skills/agdf-gate-check/SKILL.md +12 -5
  8. package/generated/.github/skills/agdf-qa-gate/SKILL.md +12 -2
  9. package/generated/.github/skills/agdf-release-or/SKILL.md +7 -2
  10. package/generated/.github/skills/agdf-runtime-contract.md +11 -812
  11. package/generated/.github/skills/agdf-task-plan-review/SKILL.md +10 -1
  12. package/generated/.github/skills/contracts/closeout.md +29 -0
  13. package/generated/.github/skills/contracts/context-graph.md +48 -0
  14. package/generated/.github/skills/contracts/control-scaffold.md +109 -0
  15. package/generated/.github/skills/contracts/gate-transition.md +134 -0
  16. package/generated/.github/skills/contracts/interaction.md +370 -0
  17. package/generated/.github/skills/contracts/modes.md +91 -0
  18. package/generated/.github/skills/contracts/quality.md +100 -0
  19. package/generated/.opencode/AGDF.md +9 -1
  20. package/generated/.opencode/agdf-runtime-contract.md +11 -812
  21. package/generated/.opencode/contracts/closeout.md +29 -0
  22. package/generated/.opencode/contracts/context-graph.md +48 -0
  23. package/generated/.opencode/contracts/control-scaffold.md +109 -0
  24. package/generated/.opencode/contracts/gate-transition.md +134 -0
  25. package/generated/.opencode/contracts/interaction.md +370 -0
  26. package/generated/.opencode/contracts/modes.md +91 -0
  27. package/generated/.opencode/contracts/quality.md +100 -0
  28. package/generated/.opencode/skills/agdf-brownfield-analysis/SKILL.md +6 -2
  29. package/generated/.opencode/skills/agdf-clean-implementation-review/SKILL.md +9 -1
  30. package/generated/.opencode/skills/agdf-code-review/SKILL.md +9 -1
  31. package/generated/.opencode/skills/agdf-delivery-closeout/SKILL.md +5 -1
  32. package/generated/.opencode/skills/agdf-delivery-path-search/SKILL.md +5 -1
  33. package/generated/.opencode/skills/agdf-gate-check/SKILL.md +12 -5
  34. package/generated/.opencode/skills/agdf-qa-gate/SKILL.md +12 -2
  35. package/generated/.opencode/skills/agdf-release-or/SKILL.md +7 -2
  36. package/generated/.opencode/skills/agdf-task-plan-review/SKILL.md +10 -1
  37. package/generated/AGENTS.md +9 -1
  38. package/generated/plugins/agdf/.codex-plugin/plugin.json +4 -4
  39. package/generated/plugins/agdf/meta/agdf-agent-router.md +9 -1
  40. package/generated/plugins/agdf/meta/agdf-plugin.definition.json +14 -8
  41. package/generated/plugins/agdf/meta/agdf-runtime-contract.md +11 -812
  42. package/generated/plugins/agdf/meta/contracts/closeout.md +29 -0
  43. package/generated/plugins/agdf/meta/contracts/context-graph.md +48 -0
  44. package/generated/plugins/agdf/meta/contracts/control-scaffold.md +109 -0
  45. package/generated/plugins/agdf/meta/contracts/gate-transition.md +134 -0
  46. package/generated/plugins/agdf/meta/contracts/interaction.md +370 -0
  47. package/generated/plugins/agdf/meta/contracts/modes.md +91 -0
  48. package/generated/plugins/agdf/meta/contracts/quality.md +100 -0
  49. package/generated/plugins/agdf/skills/brownfield-analysis/SKILL.md +6 -2
  50. package/generated/plugins/agdf/skills/clean-implementation-review/SKILL.md +9 -1
  51. package/generated/plugins/agdf/skills/code-review/SKILL.md +9 -1
  52. package/generated/plugins/agdf/skills/delivery-closeout/SKILL.md +5 -1
  53. package/generated/plugins/agdf/skills/delivery-path-search/SKILL.md +5 -1
  54. package/generated/plugins/agdf/skills/gate-check/SKILL.md +12 -5
  55. package/generated/plugins/agdf/skills/qa-gate/SKILL.md +12 -2
  56. package/generated/plugins/agdf/skills/release-or/SKILL.md +7 -2
  57. package/generated/plugins/agdf/skills/task-plan-review/SKILL.md +10 -1
  58. package/package.json +1 -1
@@ -13,7 +13,11 @@ The search is advisory and read-only. Canonical AGDF `gate-check` remains the on
13
13
 
14
14
  ## Runtime Contract
15
15
 
16
- Use `../../meta/agdf-runtime-contract.md` for canonical gate state, output discipline and Delivery Path Search boundaries. This skill must not maintain a second gate or scoring model.
16
+ Use these focused runtime-contract modules:
17
+
18
+ - `../../meta/contracts/control-scaffold.md`
19
+ - `../../meta/contracts/gate-transition.md`
20
+ - `../../meta/contracts/quality.md`
17
21
 
18
22
  ## Trigger
19
23
 
@@ -18,8 +18,14 @@ Determine the earliest blocking user approval gate and derive:
18
18
  This skill must not create later artefacts such as PRD, SD, TP, CD, CR, QA, or UAT when the gate does not allow them.
19
19
 
20
20
  ## Runtime Contract
21
- Use `../../meta/agdf-runtime-contract.md` for gate terms, closeout discipline, and non-duplication rules.
22
- The canonical gate order and transition model live only in the Runtime Contract. This skill evaluates the current state against that model; it must not maintain a second complete gate table.
21
+ Use these focused runtime-contract modules:
22
+
23
+ - `../../meta/contracts/gate-transition.md`
24
+ - `../../meta/contracts/interaction.md`
25
+ - `../../meta/contracts/control-scaffold.md`
26
+ - `../../meta/contracts/modes.md`
27
+ - `../../meta/contracts/quality.md`
28
+ The canonical gate order and transition model live only in `../../meta/contracts/gate-transition.md`. This skill evaluates the current state against that model; it must not maintain a second complete gate table.
23
29
 
24
30
  ## Agent-Native Control Path
25
31
 
@@ -69,7 +75,7 @@ For a ready `gate_approval`:
69
75
  7. Distinguish internal process steps from user decisions in natural language. For example, after `Approval: TP`, say that pre-implementation Brownfield Analysis runs next and that no further user action is required now; do not expose `next_user_gate: none` or `user_action_required: no`, and do not ask for a second approval for Brownfield Analysis.
70
76
  8. Ask exactly one question that names the selected `run_id` and `current_gate`.
71
77
  9. Offer options in stable order: exact `Approval: <GateName>`, localized revise and localized decline. Add explicit cancel only where supported after decline; otherwise host dismissal maps to cancel. Never preselect, skip, auto-submit or reorder an option.
72
- 10. Use the surface adapter declared in the canonical plugin definition only when it can wait for deliberate input without auto-resolution; otherwise request the same exact approval in concise text.
78
+ 10. Use the surface adapter declared in the canonical plugin definition only when it can wait for deliberate input without auto-resolution and can transport `exact_option_value` or `separate_label_and_value`; never invoke a `decorated_label_only` adapter. Otherwise request the same exact approval in concise text.
73
79
  11. Render both cards once in that single complete assistant message. Never merge, reverse, omit or duplicate them; the action heading does not replace either card. If the native attempt is unavailable or not applied, continue to exact text without repeating either card.
74
80
  12. Re-run gate evaluation for the same run and expected gate after the response and immediately before persistence.
75
81
  13. Reject a missing artefact, ambiguous or wrong run, wrong gate, stale expected gate, timeout/default, hook-supplied answer, agent message, technical permission outcome or plan approval.
@@ -88,7 +94,7 @@ For the transition card, use the complete resolved locale pack. The initial Germ
88
94
 
89
95
  The primary option is derived exactly as `Approval: <GateName>` from the evaluated current gate; only explanatory copy and non-authoritative outcome labels are localized. Concrete localized copy belongs to the user-facing interaction layer or the approved delivery artefact, not to English runtime rules.
90
96
 
91
- Make exactly one native-attempt for the ready gate. If the host does not render,
97
+ Make exactly one native-attempt for the eligible ready gate. If the host does not render,
92
98
  apply or safely return the native question on that attempt, switch immediately
93
99
  to the exact textual approval. Do not ask the user to request the buttons again
94
100
  and do not create a retry loop or simulated control.
@@ -102,7 +108,7 @@ only after fresh run/gate/artefact revalidation; never retry automatically.
102
108
 
103
109
  Surface behavior:
104
110
 
105
- - Codex: invoke the native short-question/request-user-input control on the first eligible attempt when callable, ask one gate question and omit auto-resolution; if it is not rendered or applied, use exact text immediately.
111
+ - Codex: invoke the native short-question/request-user-input control only when preflight proves `exact_option_value` or `separate_label_and_value`, and omit auto-resolution. The canonical `decorated_label_only` capability must use exact text without invoking the adapter. `Approval: <GateName> (Recommended)` is never a valid option or approval.
106
112
  - Claude Code: invoke `AskUserQuestion` on the first eligible attempt only when no timeout can auto-continue and no hook supplies `answers` or `updatedInput`; if it is not rendered or applied, use exact text immediately. Claude permissions and `ExitPlanMode` remain separate.
107
113
  - OpenCode: use built-in `question` when permitted. Preserve explicit `permission.question` denial and use exact text in that case. `once`, `always`, `reject` and auto mode never become gate input.
108
114
  - Other, unavailable or non-interactive surfaces: use exact textual approval and wait for a new explicit user response.
@@ -232,6 +238,7 @@ from the same snapshot and are shown exactly once.
232
238
 
233
239
  If this skill creates or updates control artefacts, do not paste full file bodies into the chat.
234
240
  List paths, summarize the decision, name the blocker or approval needed, and keep the durable content in the files.
241
+ See the Runtime Contract §Chat and Tool-Call Discipline for tool-call batching and skill output compaction rules.
235
242
 
236
243
  ## Forbidden
237
244
  This skill must not:
@@ -22,7 +22,11 @@ It answers:
22
22
  - whether blockers, critical risks, or missing evidence remain
23
23
 
24
24
  ## Runtime Contract
25
- Use `../../meta/agdf-runtime-contract.md` for Quality Contract output, Context Graph fields, gate terms, and non-duplication rules.
25
+ Use these focused runtime-contract modules:
26
+
27
+ - `../../meta/contracts/quality.md`
28
+ - `../../meta/contracts/context-graph.md`
29
+ - `../../meta/contracts/gate-transition.md`
26
30
 
27
31
  QA-specific `decision` is exactly `pass | revise | block`.
28
32
  `pass` is allowed only when TP coverage, Brownfield fit, solution integrity, and relevant documentation/Context Graph impact are sufficiently evidenced.
@@ -100,7 +104,13 @@ Use this shape:
100
104
  - impact_codes:
101
105
  ```
102
106
 
103
- If Context Graph impact is relevant, include the fields from `../../meta/agdf-runtime-contract.md`.
107
+ If Context Graph impact is relevant, include the fields from `../../meta/contracts/context-graph.md`.
108
+
109
+ ### Compact Chat Output
110
+
111
+ At `pass`: one line — `QA: pass — <one-line summary>`. Reference the durable QA report
112
+ path. Do not show the Quality Readiness projection or evidence inventory in chat.
113
+ At `revise`/`block`: show the decisive dimension, reason and next action.
104
114
 
105
115
  ## Decision Guidance
106
116
  - `pass`: required TP tasks are done, evidence is strong, no blocking Brownfield or solution-integrity risk remains.
@@ -25,7 +25,12 @@ It reports:
25
25
  - whether further quality follow-up or a separate delivery closeout is useful
26
26
 
27
27
  ## Runtime Contract
28
- Use `../../meta/agdf-runtime-contract.md` for Quality Contract output, Context Graph fields, gate terms, and non-duplication rules.
28
+ Use these focused runtime-contract modules:
29
+
30
+ - `../../meta/contracts/closeout.md`
31
+ - `../../meta/contracts/quality.md`
32
+ - `../../meta/contracts/context-graph.md`
33
+ - `../../meta/contracts/control-scaffold.md`
29
34
 
30
35
  OR-specific output must make gate status, delivered and intentionally not delivered content, missing approvals, missing evidence, risks, retained fallbacks, and the next permissible step visible.
31
36
  When `.agdf/control/` is present, persist or link the OR under `.agdf/control/artefacts/<key>/OR.md` and reference it from the selected canonical `RUN_STATE.md` or `MASTER_BACKLOG.md` when it is steering-relevant.
@@ -118,7 +123,7 @@ Use a compact structure:
118
123
  - quality_outlook:
119
124
  ```
120
125
 
121
- When Context Graph impact is relevant, include the fields from `../../meta/agdf-runtime-contract.md`.
126
+ When Context Graph impact is relevant, include the fields from `../../meta/contracts/context-graph.md`.
122
127
  Include `context_graph_reconciliation` whenever Context Graph impact is present. If the value is `open_gap`, required next step must resolve or explicitly retain that gap before commit-ready or release-ready handoff.
123
128
 
124
129
  ## Forbidden
@@ -19,7 +19,11 @@ For each relevant task, this skill determines:
19
19
  This skill provides TP coverage. It is not the final QA decision.
20
20
 
21
21
  ## Runtime Contract
22
- Use `../../meta/agdf-runtime-contract.md` for Quality Contract output, Context Graph fields, gate terms, and non-duplication rules.
22
+ Use these focused runtime-contract modules:
23
+
24
+ - `../../meta/contracts/quality.md`
25
+ - `../../meta/contracts/context-graph.md`
26
+ - `../../meta/contracts/gate-transition.md`
23
27
 
24
28
  TP-specific output must evaluate every relevant `task_id` with completion status, AC coverage, evidence, missing evidence, and QA-relevant gaps.
25
29
  If `context_graph_required_action` is not `none`, the affected task is complete only if follow-up, evidence, or an intentionally open gap is visible.
@@ -105,6 +109,11 @@ Evidence confidence:
105
109
  - `medium`
106
110
  - `low`
107
111
 
112
+ ### Compact Chat Output
113
+
114
+ At `pass`: one line — `TP Review: pass — <X>/<total> tasks fully_done`.
115
+ At `revise`/`block`: show incomplete tasks with missing evidence.
116
+
108
117
  ## Forbidden
109
118
  This skill must not:
110
119
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "create-agdf",
3
- "version": "0.8.7",
3
+ "version": "0.9.0",
4
4
  "description": "Bootstrap AGDF repository-local plugin files, Copilot/OpenCode instructions, skills, control files and machine-readable checks.",
5
5
  "type": "module",
6
6
  "files": [