@syntesseraai/opencode-feature-factory 0.6.17 → 0.6.19

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.
@@ -9,18 +9,3 @@ return:
9
9
  - /pipeline/building/implement-batch {as:build-implementation} $RESULT[build-batches]
10
10
  - /pipeline/reviewing/run {as:review-phase} $RESULT[build-implementation]
11
11
  ---
12
-
13
- Run build phase from the approved final plan passed in `$ARGUMENTS`.
14
-
15
- Rules:
16
-
17
- 1. If `PLANNING_PROCEED=NO` appears in input, stop and return user-confirmation-required context instead of executing build tasks.
18
- 2. Maintain dependency-safe batching.
19
- 3. Only parallelize tasks with no dependency edges.
20
- 4. Pass intermediate outputs via `{as:name}` and `$RESULT[name]`.
21
- 5. Implementation is codex-focused via frontmatter model declaration in `implement-batch`.
22
- 6. Send completed implementation output into reviewing via `/pipeline/reviewing/run`.
23
-
24
- Orchestrator constraint:
25
-
26
- This command is a **dispatch orchestrator only**. You must NOT directly read, edit, modify, write, or create any code files, configuration files, or repository files. Your sole responsibility is to invoke the declared sub-commands, pass structured data between them via `{as:name}` / `$RESULT[name]`, evaluate gate conditions, and route execution. All file-touching work belongs exclusively to the sub-commands (`breakdown`, `validate-batch`, `implement-batch`).
@@ -12,20 +12,3 @@ return:
12
12
  - /pipeline/documentation/gate $RESULT[doc-review]
13
13
  - If `DOCUMENTATION_GATE=REWORK`, continue loop with review feedback for the next document pass.
14
14
  ---
15
-
16
- Execute the documentation stage for the current approved implementation.
17
-
18
- Orchestrator constraint:
19
-
20
- This command is a **dispatch orchestrator only**. You must NOT directly read, edit, modify, write, or create any code files, configuration files, or repository files. Your sole responsibility is to invoke the declared sub-commands (`document`, `review`, `gate`), pass structured data between them via `{as:name}` / `$RESULT[name]`, evaluate gate/loop conditions, and route execution. All file-touching work belongs exclusively to the leaf sub-commands.
21
-
22
- Skill requirements:
23
-
24
- 1. ChatGPT supervisor must load `ff-todo-management` to track documentation actions and rework items per iteration.
25
- 2. Documentation reviewer should use `ff-severity-classification` when reporting documentation issues.
26
-
27
- Stop criteria:
28
-
29
- - approve when documentation reviewer confirms documentation is complete, accurate, and repository docs are updated
30
- - continue loop while unresolved documentation issues exist and iteration < 5
31
- - escalate to user when iteration reaches 5 without approval
@@ -11,20 +11,3 @@ return:
11
11
  - /pipeline/planning/synthesize {as:plan-consensus} $RESULT[plan-opus] $RESULT[plan-gemini] $RESULT[plan-codex]
12
12
  - /pipeline/planning/gate $RESULT[plan-consensus]
13
13
  ---
14
-
15
- Run one complete planning iteration for the active pipeline.
16
-
17
- Orchestrator constraint:
18
-
19
- This command is a **dispatch orchestrator only**. You must NOT directly read, edit, modify, write, or create any code files, configuration files, or repository files. Your sole responsibility is to invoke the declared sub-commands (`plan`, `synthesize`, `gate`), pass structured data between them via `{as:name}` / `$RESULT[name]`, evaluate gate conditions, and route execution. All file-touching work belongs exclusively to the leaf sub-commands.
20
-
21
- Requirements brief:
22
-
23
- $ARGUMENTS
24
-
25
- Rules:
26
-
27
- 1. Keep each planner output structured and concise for synthesis.
28
- 2. Pass outputs using `{as:name}` and `$RESULT[name]` rather than intermediate files.
29
- 3. Each planning model must include architecture validation in its proposal.
30
- 4. Continue only through gate outcomes defined in `/pipeline/planning/gate`.
@@ -17,15 +17,3 @@ return:
17
17
  - /pipeline/reviewing/gate $RESULT[review-synthesis]
18
18
  - If `REVIEW_GATE=REWORK`, invoke `/pipeline/building/implement-batch` to apply fixes before the next loop iteration.
19
19
  ---
20
-
21
- Execute the review loop for the current completed tasks/rework report.
22
-
23
- Orchestrator constraint:
24
-
25
- This command is a **dispatch orchestrator only**. You must NOT directly read, edit, modify, write, or create any code files, configuration files, or repository files. Your sole responsibility is to invoke the declared sub-commands (`triage`, `review`, `synthesize`, `gate`, and rework dispatch), pass structured data between them via `{as:name}` / `$RESULT[name]`, evaluate gate/loop conditions, and route execution. All file-touching work belongs exclusively to the leaf sub-commands.
26
-
27
- Stop criteria:
28
-
29
- - approve when `>=95` confidence and zero unresolved issues
30
- - continue loop while unresolved issues exist and iteration < 10
31
- - escalate to user when iteration reaches 10 without approval
@@ -4,26 +4,9 @@ subtask: true
4
4
  agent: general
5
5
  model: openai/gpt-5.4
6
6
  return:
7
- - /pipeline/planning/run {as:planning-phase && loop:5 && until:planning gate is APPROVED or planning gate is BLOCKED and waiting for user confirmation}
7
+ - /pipeline/planning/run {as:planning-phase && loop:5 && until:planning gate is APPROVED or planning gate is BLOCKED and waiting for user confirmation} $ARGUMENTS
8
8
  - /pipeline/planning/confirm {as:planning-decision} $RESULT[planning-phase]
9
9
  - /pipeline/building/run {as:build-phase} $RESULT[planning-decision]
10
10
  - /pipeline/documentation/run $RESULT[build-phase]
11
11
  - /pipeline/complete
12
12
  ---
13
-
14
- Start the deterministic Feature Factory pipeline with this requirements brief:
15
-
16
- $ARGUMENTS
17
-
18
- Execution requirements:
19
-
20
- 1. You are already inside `/pipeline/start`; do not invoke `/pipeline/start` again.
21
- 2. Execute the declared return chain directly from this command.
22
- 3. Use `{as:name}` and `$RESULT[name]` for phase-to-phase handoff.
23
- 4. Avoid file persistence for intermediate artifacts unless a command explicitly requires audit snapshots.
24
- 5. Use command chaining, parallel fan-out, and loop gates from the `/pipeline/...` command tree.
25
- 6. Do not skip planning, review, and documentation gates.
26
-
27
- Orchestrator constraint:
28
-
29
- This command is a **top-level dispatch orchestrator only**. You must NOT directly read, edit, modify, write, or create any code files, configuration files, or repository files. Your sole responsibility is to invoke the declared phase commands in order, pass structured data between them via `{as:name}` / `$RESULT[name]`, and evaluate gate conditions. All file-touching work belongs exclusively to the leaf sub-commands within each phase.
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "$schema": "https://json.schemastore.org/package.json",
3
3
  "name": "@syntesseraai/opencode-feature-factory",
4
- "version": "0.6.17",
4
+ "version": "0.6.19",
5
5
  "type": "module",
6
6
  "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
7
7
  "license": "MIT",