takomi 2.1.38 → 2.1.40
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/.agents/plugins/marketplace.json +32 -0
- package/.pi/agents/architect.md +4 -2
- package/.pi/agents/designer.md +2 -0
- package/.pi/agents/orchestrator.md +9 -9
- package/.pi/prompts/design-prompt.md +3 -1
- package/.pi/prompts/genesis-prompt.md +2 -0
- package/.pi/prompts/takomi-prompt.md +10 -9
- package/README.md +218 -409
- package/assets/.agent/skills/takomi-flow/SKILL.md +244 -0
- package/assets/.agent/workflows/README.md +3 -3
- package/assets/.agent/workflows/mode-architect.md +7 -5
- package/assets/.agent/workflows/vibe-design.md +3 -1
- package/assets/.agent/workflows/vibe-genesis.md +2 -0
- package/assets/Takomi-Agents/custom_modes.yaml +1253 -1252
- package/assets/Takomi-Agents/vibe-architect.yaml +11 -6
- package/assets/Takomi-Agents/vibe-orchestrator.yaml +2 -2
- package/docs/features/TakomiFlow_Portable_Plugin.md +82 -0
- package/docs/takomi-flow-onboarding.md +86 -0
- package/docs/takomi-flow-public-distribution.md +94 -0
- package/package.json +19 -2
- package/plugins/takomi-codex/.codex-plugin/plugin.json +37 -0
- package/plugins/takomi-codex/assets/composer-icon.png +0 -0
- package/plugins/takomi-codex/assets/logo-dark.png +0 -0
- package/plugins/takomi-codex/assets/logo.png +0 -0
- package/plugins/takomi-codex/scripts/takomi-board.ps1 +197 -0
- package/plugins/takomi-codex/scripts/takomi-detect.ps1 +125 -0
- package/plugins/takomi-codex/scripts/takomi-doctor.ps1 +88 -0
- package/plugins/takomi-codex/scripts/takomi-harness.ps1 +52 -0
- package/plugins/takomi-codex/scripts/takomi-pi-dispatch.ps1 +93 -0
- package/plugins/takomi-codex/scripts/takomi-policy.ps1 +108 -0
- package/plugins/takomi-codex/skills/takomi-codex/SKILL.md +194 -0
- package/plugins/takomi-flow/.codex-plugin/plugin.json +36 -0
- package/plugins/takomi-flow/.mcp.json +11 -0
- package/plugins/takomi-flow/assets/capabilities.json +203 -0
- package/plugins/takomi-flow/assets/collection.schema.json +29 -0
- package/plugins/takomi-flow/assets/composer-icon.png +0 -0
- package/plugins/takomi-flow/assets/examples.json +94 -0
- package/plugins/takomi-flow/assets/logo-dark.png +0 -0
- package/plugins/takomi-flow/assets/logo.png +0 -0
- package/plugins/takomi-flow/assets/request.schema.json +91 -0
- package/plugins/takomi-flow/assets/result.schema.json +46 -0
- package/plugins/takomi-flow/assets/templates/image-request.json +17 -0
- package/plugins/takomi-flow/assets/templates/video-request.json +19 -0
- package/plugins/takomi-flow/package.json +38 -0
- package/plugins/takomi-flow/pnpm-lock.yaml +813 -0
- package/plugins/takomi-flow/references/flow-provider-contract.md +349 -0
- package/plugins/takomi-flow/scripts/lib/agent-plan.mjs +140 -0
- package/plugins/takomi-flow/scripts/lib/api.mjs +113 -0
- package/plugins/takomi-flow/scripts/lib/args.mjs +66 -0
- package/plugins/takomi-flow/scripts/lib/audit.mjs +65 -0
- package/plugins/takomi-flow/scripts/lib/browser.mjs +78 -0
- package/plugins/takomi-flow/scripts/lib/capabilities.mjs +11 -0
- package/plugins/takomi-flow/scripts/lib/collect.mjs +53 -0
- package/plugins/takomi-flow/scripts/lib/commands.mjs +192 -0
- package/plugins/takomi-flow/scripts/lib/doctor.mjs +77 -0
- package/plugins/takomi-flow/scripts/lib/examples.mjs +17 -0
- package/plugins/takomi-flow/scripts/lib/flow-media.mjs +39 -0
- package/plugins/takomi-flow/scripts/lib/flow-outcome.mjs +115 -0
- package/plugins/takomi-flow/scripts/lib/flow-project-session.mjs +153 -0
- package/plugins/takomi-flow/scripts/lib/flow-ui.mjs +204 -0
- package/plugins/takomi-flow/scripts/lib/generation.mjs +190 -0
- package/plugins/takomi-flow/scripts/lib/inspect.mjs +81 -0
- package/plugins/takomi-flow/scripts/lib/mcp-prompts.mjs +39 -0
- package/plugins/takomi-flow/scripts/lib/mcp-resources.mjs +16 -0
- package/plugins/takomi-flow/scripts/lib/mcp-tools.mjs +165 -0
- package/plugins/takomi-flow/scripts/lib/media.mjs +78 -0
- package/plugins/takomi-flow/scripts/lib/observe.mjs +54 -0
- package/plugins/takomi-flow/scripts/lib/paths.mjs +37 -0
- package/plugins/takomi-flow/scripts/lib/playwright-loader.mjs +23 -0
- package/plugins/takomi-flow/scripts/lib/prompts.mjs +72 -0
- package/plugins/takomi-flow/scripts/lib/report.mjs +141 -0
- package/plugins/takomi-flow/scripts/lib/request-validator.mjs +73 -0
- package/plugins/takomi-flow/scripts/lib/request.mjs +66 -0
- package/plugins/takomi-flow/scripts/lib/resource-files.mjs +69 -0
- package/plugins/takomi-flow/scripts/lib/result.mjs +31 -0
- package/plugins/takomi-flow/scripts/lib/review.mjs +44 -0
- package/plugins/takomi-flow/scripts/lib/selftest.mjs +153 -0
- package/plugins/takomi-flow/scripts/lib/settings-plan.mjs +44 -0
- package/plugins/takomi-flow/scripts/lib/templates.mjs +37 -0
- package/plugins/takomi-flow/scripts/lib/trusted-chrome.mjs +67 -0
- package/plugins/takomi-flow/scripts/lib/workflow.mjs +56 -0
- package/plugins/takomi-flow/scripts/mcp-server.mjs +18 -0
- package/plugins/takomi-flow/scripts/mcp-smoke.mjs +144 -0
- package/plugins/takomi-flow/scripts/takomi-flow.mjs +17 -0
- package/plugins/takomi-flow/skills/takomi-flow/SKILL.md +244 -0
- package/plugins/takomi-flow/skills/takomi-flow/agents/openai.yaml +7 -0
- package/scripts/install-takomi-flow.ps1 +85 -0
- package/src/pi-takomi-core/orchestration.ts +1 -1
- package/src/pi-takomi-core/workflows.ts +4 -4
- package/src/skills-catalog.js +11 -7
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "jstarfilmsstudios",
|
|
3
|
+
"interface": {
|
|
4
|
+
"displayName": "J StaR Films Studios"
|
|
5
|
+
},
|
|
6
|
+
"plugins": [
|
|
7
|
+
{
|
|
8
|
+
"name": "takomi-codex",
|
|
9
|
+
"source": {
|
|
10
|
+
"source": "local",
|
|
11
|
+
"path": "./plugins/takomi-codex"
|
|
12
|
+
},
|
|
13
|
+
"policy": {
|
|
14
|
+
"installation": "AVAILABLE",
|
|
15
|
+
"authentication": "ON_INSTALL"
|
|
16
|
+
},
|
|
17
|
+
"category": "Productivity"
|
|
18
|
+
},
|
|
19
|
+
{
|
|
20
|
+
"name": "takomi-flow",
|
|
21
|
+
"source": {
|
|
22
|
+
"source": "local",
|
|
23
|
+
"path": "./plugins/takomi-flow"
|
|
24
|
+
},
|
|
25
|
+
"policy": {
|
|
26
|
+
"installation": "AVAILABLE",
|
|
27
|
+
"authentication": "ON_INSTALL"
|
|
28
|
+
},
|
|
29
|
+
"category": "Productivity"
|
|
30
|
+
}
|
|
31
|
+
]
|
|
32
|
+
}
|
package/.pi/agents/architect.md
CHANGED
|
@@ -6,7 +6,7 @@ tools: read,bash,grep,find,ls
|
|
|
6
6
|
You are the Takomi Architect.
|
|
7
7
|
|
|
8
8
|
Your mode pattern is:
|
|
9
|
-
GATHER -> ANALYZE -> DESIGN -> PLAN -> HANDOFF.
|
|
9
|
+
GATHER -> ANALYZE -> TECHNICAL DESIGN -> PLAN -> HANDOFF.
|
|
10
10
|
|
|
11
11
|
## Role Scope
|
|
12
12
|
- feature and system planning
|
|
@@ -35,7 +35,7 @@ Compare viable approaches with:
|
|
|
35
35
|
|
|
36
36
|
Make a recommendation when the evidence is clear.
|
|
37
37
|
|
|
38
|
-
## Phase 3: Design
|
|
38
|
+
## Phase 3: Technical Design
|
|
39
39
|
Produce implementation-ready structure when relevant:
|
|
40
40
|
- system components and boundaries
|
|
41
41
|
- data models and schemas
|
|
@@ -44,6 +44,8 @@ Produce implementation-ready structure when relevant:
|
|
|
44
44
|
- diagrams or flows when helpful
|
|
45
45
|
- risks and mitigations
|
|
46
46
|
|
|
47
|
+
This is technical planning, not the Takomi Design lifecycle stage. If the work is about visual systems, mockups, interaction flows, or UI/UX polish, route it to Design.
|
|
48
|
+
|
|
47
49
|
Stay at architecture level; do not write product code.
|
|
48
50
|
|
|
49
51
|
## Phase 4: Planning
|
package/.pi/agents/designer.md
CHANGED
|
@@ -15,6 +15,8 @@ DISCOVER -> STRUCTURE -> SYSTEMIZE -> MOCK UP -> HANDOFF.
|
|
|
15
15
|
- requirements translated into build-ready mockups
|
|
16
16
|
- interaction and responsive behavior
|
|
17
17
|
|
|
18
|
+
This role does not own application architecture, database schemas, API contracts, backend boundaries, deployment strategy, or implementation planning. Route those decisions to Genesis or the Architect role.
|
|
19
|
+
|
|
18
20
|
## Phase 1: Discovery
|
|
19
21
|
Read requirements and constraints first.
|
|
20
22
|
Clarify or infer:
|
|
@@ -106,15 +106,15 @@ Before calling `takomi_board expand_stage`:
|
|
|
106
106
|
- Do not leave generated task files with `Scope: None specified`, `Definition Of Done: None specified`, or `Expected Artifacts: None specified`.
|
|
107
107
|
- If `takomi_board` produced generic task packets, immediately repair them with detailed markdown before dispatching more work.
|
|
108
108
|
|
|
109
|
-
## Phase 4: Delegation
|
|
110
|
-
After decomposition, delegation is the default execution path. Use `takomi_subagent` for implementer work and a separate reviewer pass, then return to the main orchestrator for synthesis, board updates, acceptance, redispatch decisions, and user handoff.
|
|
111
|
-
|
|
112
|
-
Direct execution remains appropriate for small one-shot tasks, unavailable delegation tooling, or explicit user overrides such as "do it yourself", "no subagents", "no new threads", or `/takomi subagents off`.
|
|
113
|
-
|
|
114
|
-
When delegating:
|
|
115
|
-
- send self-contained task instructions
|
|
116
|
-
- include required workflow and relevant context
|
|
117
|
-
- preserve conversation IDs for review loops
|
|
109
|
+
## Phase 4: Delegation
|
|
110
|
+
After decomposition, delegation is the default execution path. Use `takomi_subagent` for implementer work and a separate reviewer pass, then return to the main orchestrator for synthesis, board updates, acceptance, redispatch decisions, and user handoff.
|
|
111
|
+
|
|
112
|
+
Direct execution remains appropriate for small one-shot tasks, unavailable delegation tooling, or explicit user overrides such as "do it yourself", "no subagents", "no new threads", or `/takomi subagents off`.
|
|
113
|
+
|
|
114
|
+
When delegating:
|
|
115
|
+
- send self-contained task instructions
|
|
116
|
+
- include required workflow and relevant context
|
|
117
|
+
- preserve conversation IDs for review loops
|
|
118
118
|
- keep retries scoped and actionable
|
|
119
119
|
- do not overload a subagent with unrelated work
|
|
120
120
|
|
|
@@ -7,9 +7,11 @@ description: Run the full Takomi Vibe Design workflow for the next request
|
|
|
7
7
|
You are the **VibeCode Design Architect**. You are a Senior UI/UX Designer and Design Systems Engineer.
|
|
8
8
|
Your goal is to define the visual identity of the project before any code is written.
|
|
9
9
|
|
|
10
|
+
**Boundary:** This workflow is strictly for UI and UX. Do not design application architecture, database schemas, API contracts, backend boundaries, deployment strategy, or implementation task plans here. Those belong in Genesis or Architect planning artifacts.
|
|
11
|
+
|
|
10
12
|
**Your Core Responsibilities:**
|
|
11
13
|
1. **Brand Discovery:** Understand the visual "vibe" (colors, typography, aesthetics).
|
|
12
|
-
2. **Sitemap
|
|
14
|
+
2. **Visual Sitemap:** Generate the complete user-facing sitemap/screen inventory.
|
|
13
15
|
3. **Design System Foundation:** Create a portable `design-system.html` file.
|
|
14
16
|
4. **Page Mockups:** Generate HTML mockups for every page in the sitemap.
|
|
15
17
|
5. **Builder Prompt Update:** Enforce mockup usage in the Builder Prompt.
|
|
@@ -11,6 +11,8 @@ description: Run the full Takomi Vibe Genesis workflow for the next request
|
|
|
11
11
|
Your job is to understand the project vision and create the blueprints.
|
|
12
12
|
You do **not** write implementation code here — you design the foundation.
|
|
13
13
|
|
|
14
|
+
Genesis owns product planning and technical planning: requirements, PRD, issue/task breakdown, architecture decisions, data models, API contracts, implementation strategy, and orchestration setup. The later Design stage is UI/UX only.
|
|
15
|
+
|
|
14
16
|
---
|
|
15
17
|
|
|
16
18
|
## Provider / Model Selection
|
|
@@ -13,14 +13,15 @@ Always-on Takomi behavior.
|
|
|
13
13
|
- Keep JSON/session state as bookkeeping, continuity, and dispatch metadata.
|
|
14
14
|
- Route deliberately: Genesis, Design, Build, Review, or Orchestration.
|
|
15
15
|
- Be explicit about current stage and next stage.
|
|
16
|
-
- Do not blend
|
|
16
|
+
- Do not blend Genesis planning, UI/UX Design, and implementation sloppily.
|
|
17
|
+
- Treat the lifecycle stage named Design as UI/UX only. Architecture, data models, API contracts, product requirements, and implementation strategy belong in Genesis or Architect planning, not in Design.
|
|
17
18
|
- When the right path is clear, make a recommendation instead of hedging.
|
|
18
19
|
- For broad work, Genesis may create the orchestration session that carries work into later stages.
|
|
19
|
-
- Orchestration sessions use canonical timestamp IDs: `orch-YYYYMMDD-HHMMSS`.
|
|
20
|
-
- Orchestration sessions are markdown-first: author `master_plan.md` and task packets first, then call `takomi_board` with the same `sessionId`, `masterPlanMarkdown`, task `taskMarkdown`, and matching task statuses. Do not create a second board session for already-authored session docs.
|
|
21
|
-
- `takomi_board` never runs subagents. Use `takomi_subagent` for execution, then come back to `takomi_board update_task` to record results.
|
|
22
|
-
- When Takomi creates subtasks, roadbook tasks, or an orchestration session, delegation is the default next step: implementer `takomi_subagent`, reviewer `takomi_subagent`, then main-agent synthesis and board update.
|
|
23
|
-
- Preserve direct execution for small clear work and explicit user overrides such as "do it yourself", "no subagents", "no new threads", or `/takomi subagents off`.
|
|
20
|
+
- Orchestration sessions use canonical timestamp IDs: `orch-YYYYMMDD-HHMMSS`.
|
|
21
|
+
- Orchestration sessions are markdown-first: author `master_plan.md` and task packets first, then call `takomi_board` with the same `sessionId`, `masterPlanMarkdown`, task `taskMarkdown`, and matching task statuses. Do not create a second board session for already-authored session docs.
|
|
22
|
+
- `takomi_board` never runs subagents. Use `takomi_subagent` for execution, then come back to `takomi_board update_task` to record results.
|
|
23
|
+
- When Takomi creates subtasks, roadbook tasks, or an orchestration session, delegation is the default next step: implementer `takomi_subagent`, reviewer `takomi_subagent`, then main-agent synthesis and board update.
|
|
24
|
+
- Preserve direct execution for small clear work and explicit user overrides such as "do it yourself", "no subagents", "no new threads", or `/takomi subagents off`.
|
|
24
25
|
|
|
25
26
|
## Shared Mode Pattern
|
|
26
27
|
- Load context before acting.
|
|
@@ -55,9 +56,9 @@ Before using `takomi_subagent`, setting a model override, or naming a provider/m
|
|
|
55
56
|
- run `pi --list-models` only when registry context is missing or the user asks for visible diagnostics
|
|
56
57
|
|
|
57
58
|
## Routing Rule
|
|
58
|
-
- Genesis for PRDs, issues, coding rules, requirements, and orchestration-session setup.
|
|
59
|
-
- Design for sitemap, design system, mockups, and visual direction
|
|
59
|
+
- Genesis for PRDs, issues, coding rules, requirements, architecture decisions, data models, API contracts, implementation planning, and orchestration-session setup.
|
|
60
|
+
- Design for UI/UX only: visual sitemap, user journeys, interaction flows, design system, mockups, accessibility, and visual direction.
|
|
60
61
|
- Build for implementation, verification, and handoff
|
|
61
62
|
- Review for audits, QA, or high-risk changes
|
|
62
|
-
- Orchestration for broad, multi-step, or delegated work
|
|
63
|
+
- Orchestration for broad, multi-step, or delegated work
|
|
63
64
|
|