Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .agents/PROJECT.md
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ content/

The skills implement a multi-phase agentic development pipeline. Entry points:

- **`/orchestrate-dev`** — full workflow (default), lightweight (`--mode=vibe`), or thorough (`--mode=strict`)
- **`/orchestrate-dev`** — full workflow (default), lightweight (`--mode=vibe`), lightweight with enforcement (`--mode=lite`), or thorough (`--mode=strict`)
- **`/orchestrate-review`** — review-only workflow for manually written code

The `orchestrate` skill is the internal pipeline engine. It:
Expand Down
22 changes: 12 additions & 10 deletions packages/agents/content/skills/orchestrate-dev/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ Run a full development workflow by invoking the `orchestrate` engine with the co
## Arguments

- Task description (required): what to implement
- `--mode=<vibe|strict>`: select a mode preset (default: no mode, preserving current behavior)
- `--mode=<vibe|lite|strict>`: select a mode preset (default: no mode, preserving current behavior)
- `--max-review-rounds=N`: maximum iterative review rounds (default: 3)
- `--diff-base=<ref>`: reference to diff against for reviews (default: project's default branch)
- `--approval-threshold=<low|medium|high>`: findings at this level or above must be fixed for code approval (default: `low`)
Expand All @@ -26,14 +26,14 @@ Run a full development workflow by invoking the `orchestrate` engine with the co

Each mode is a preset bundle of settings. When `--mode` is specified, its preset values apply as defaults. Any setting can be individually overridden via explicit CLI arguments (e.g., `--mode=vibe --approval-threshold=medium`).

| Setting | `vibe` | (default) | `strict` |
| ------------------- | ------ | --------- | -------- |
| architecture | absent | optional | required |
| planning | absent | optional | required |
| approval-threshold | high | low | low |
| budget-threshold | high | low | low |
| holistic_reviewer\* | sonnet | opus | opus |
| max-review-rounds | 1 | 3 | 4 |
| Setting | `vibe` | `lite` | (default) | `strict` |
| ------------------- | ------ | ------ | --------- | -------- |
| architecture | absent | absent | optional | required |
| planning | absent | absent | optional | required |
| approval-threshold | high | low | low | low |
| budget-threshold | high | low | low | low |
| holistic_reviewer\* | sonnet | sonnet | opus | opus |
| max-review-rounds | 1 | 2 | 3 | 4 |

\* `holistic_reviewer` uses snake_case because it is a `--models` key (passed as `--models=holistic_reviewer:sonnet`), not a standalone argument. See the engine's [model resolution](../orchestrate/SKILL.md#resolving-models) for details.

Expand Down Expand Up @@ -62,7 +62,7 @@ architecture (optional) -> planning (optional) -> implementation (required) -> r
| `implementation` | `required` | Write code |
| `review-cycle` | `required` | Parallel review, code-simplifier, holistic review |

**`--mode=vibe`**:
**`--mode=vibe` and `--mode=lite`**:

```
implementation (required) -> review-cycle (required)
Expand All @@ -73,6 +73,8 @@ implementation (required) -> review-cycle (required)
| `implementation` | `required` | Write code |
| `review-cycle` | `required` | Parallel review, code-simplifier, holistic review |

Both modes skip architecture and planning. They differ in review strictness -- see the mode preset table above.

**`--mode=strict`**:

```
Expand Down
2 changes: 1 addition & 1 deletion packages/agents/content/skills/orchestrate/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ user-invocable: false

You are a pipeline execution engine for multi-phase development workflows. You delegate ALL work to specialized subagents via the **Task tool** and use their structured output for flow control. You never write project code directly — only orchestration artifacts (run-manifest, run-summary). Run state is managed via MCP tool calls (`init_run`, `emit_event`, `register_artifact`, `complete_run`, `get_run_state`).

Wrapper skills (`orchestrate-dev` with optional `--mode=vibe|strict`, `orchestrate-review`) configure which phases to run and invoke this engine with a pipeline specification.
Wrapper skills (`orchestrate-dev` with optional `--mode=vibe|lite|strict`, `orchestrate-review`) configure which phases to run and invoke this engine with a pipeline specification.

## Arguments

Expand Down