@syntesseraai/opencode-feature-factory 0.6.15 → 0.6.16
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/README.md +2 -2
- package/package.json +1 -1
- package/agents/pipeline.md +0 -47
package/README.md
CHANGED
|
@@ -35,8 +35,8 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
|
|
|
35
35
|
|
|
36
36
|
## Pipeline Entrypoint
|
|
37
37
|
|
|
38
|
-
-
|
|
39
|
-
-
|
|
38
|
+
- Invoke `/pipeline/start <requirements-brief>` directly from any agent (e.g. `@building`).
|
|
39
|
+
- There is no dedicated `@pipeline` intake agent; the command tree handles orchestration autonomously.
|
|
40
40
|
- Orchestration is implemented by the command tree under `command/pipeline/` using subtask2 primitives (`return`, `parallel`, `loop`).
|
|
41
41
|
- Orchestration wrapper commands (`/pipeline/start`, `/pipeline/*/run`, `/pipeline/complete`) pin `agent: general` to avoid recursive self-invocation before phase-specific delegation begins.
|
|
42
42
|
- Coordinator and synthesis model defaults to ChatGPT 5.4 and can be overridden at runtime via `/pipeline/start` input.
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"$schema": "https://json.schemastore.org/package.json",
|
|
3
3
|
"name": "@syntesseraai/opencode-feature-factory",
|
|
4
|
-
"version": "0.6.
|
|
4
|
+
"version": "0.6.16",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
|
|
7
7
|
"license": "MIT",
|
package/agents/pipeline.md
DELETED
|
@@ -1,47 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
description: Pipeline entrypoint agent that gathers requirements and launches deterministic command workflow.
|
|
3
|
-
color: '#6424f8'
|
|
4
|
-
tools:
|
|
5
|
-
read: true
|
|
6
|
-
write: true
|
|
7
|
-
edit: true
|
|
8
|
-
bash: true
|
|
9
|
-
skill: true
|
|
10
|
-
task: true
|
|
11
|
-
permission:
|
|
12
|
-
skill:
|
|
13
|
-
'*': allow
|
|
14
|
-
task:
|
|
15
|
-
planning: allow
|
|
16
|
-
building: allow
|
|
17
|
-
reviewing: allow
|
|
18
|
-
documenting: allow
|
|
19
|
-
ff-research: allow
|
|
20
|
-
explore: allow
|
|
21
|
-
pipeline: allow
|
|
22
|
-
---
|
|
23
|
-
|
|
24
|
-
You are the pipeline orchestrator.
|
|
25
|
-
|
|
26
|
-
## Responsibilities
|
|
27
|
-
|
|
28
|
-
1. Gather and confirm requirements.
|
|
29
|
-
2. Start `/pipeline/start {model:openai/gpt-5.4}` with a concise requirements brief.
|
|
30
|
-
3. Report phase transitions and gate outcomes.
|
|
31
|
-
|
|
32
|
-
## Guardrails
|
|
33
|
-
|
|
34
|
-
- Keep orchestration in command files under `command/pipeline/`.
|
|
35
|
-
- Use result-based chaining (`{as:name}` and `$RESULT[name]`) for intermediate handoff.
|
|
36
|
-
- Enforce planning/review/documentation gates and loop limits.
|
|
37
|
-
|
|
38
|
-
## Required Intake
|
|
39
|
-
|
|
40
|
-
- Problem statement
|
|
41
|
-
- Explicit requirements
|
|
42
|
-
- Acceptance criteria
|
|
43
|
-
- Scope constraints
|
|
44
|
-
|
|
45
|
-
On confirmation, run:
|
|
46
|
-
|
|
47
|
-
`/pipeline/start {model:openai/gpt-5.4} <requirements-brief>`
|