The Strategic Delivery kit gives your AI one chain from strategy to execution: Goal sets a measurable target, Feature turns it into initiatives with plans, Plan writes phases, and Phase executes them. Each level waits for the level below, and you approve the target, every breakdown and every verification.
4 templates · 25 steps · 8 approvals · 5 loops back
one chip per stored step · square chips wait for a person
Four workflow templates, installed together. Each one is a stored workflow your AI client receives one step at a time over MCP.
01 · 4 steps · 2 approvals
Drive strategic objectives from definition to completion. The AI drives through Capture, Active tracking, and Review.
02 · 7 steps · 2 approvals
Deliver features from requirements to reviewed release. The AI drives through Capture, planning, execution, and Verify.
03 · 10 steps · 3 approvals
Turn strategic work into reviewed, executable plans. The AI drives through Analyze, Draft, phases, and execution.
04 · 4 steps · 1 approval
Execute an implementation phase from ready to verified. The AI drives through Ready, Implement, and Verify.
Four levels, one tree. A goal stays active while initiatives sit under it. Each initiative runs the Feature workflow and creates child plans. Each plan creates child phases. Nothing above closes until everything below is completed or cancelled, so a goal marked done means its work is actually done.
| From | To | How the work moves |
|---|---|---|
| Goal | Feature | Active holds the goal while initiatives are linked under it; the step waits for child work and allows an empty start. |
| Feature | Plan | Create Plans makes one child plan per approved item; Execute Plans waits for all of them. |
| Plan | Phase | Create Phases makes one child task per phase file; Execute Phases waits for all of them. |
A parent step that waits on children holds until every child task is completed or cancelled. Each child runs its own workflow, and its steps run one after another.
Every approval step in the kit, read from the stored workflows. The run holds at each one until you answer.
| Template | Approval step | If you reject |
|---|---|---|
| Goal | Capture step 1 | no rejection path; approve to continue |
| Review step 3 | back to Active | |
| Feature | Define Plans step 2 | no rejection path; approve to continue |
| Verify step 5 | back to Execute Plans | |
| Plan | Review step 5 | back to Apply Fixes |
| Ready to Execute step 7 | no rejection path; approve to continue | |
| Verify step 9 | back to Execute Phases | |
| Phase | Verify step 3 | back to Implement |
An illustrative run, labelled as an example. The step names are the templates' real steps.
Goal Capture records the metric, the timeline and how success is measured. You approve the target.
Two Feature runs start under the active goal. Each proposes its plans, and you approve each breakdown.
Each plan writes phase files, you review, and phase tasks run and verify one by one.
Goal Review reports linked work and progress on the metric. You approve the close, or reject to keep it active.
Connect your AI client first, then install the kit from the catalog in the ConvOps app. See how to connect a client
Installed templates are workflows in your workspace. Ask your AI to change one in plain words; the edit lands on the step that needs it.
new chat
more example prompts
Yes. Goal Active accepts initiatives for committed bodies of work and direct tasks or bugs for standalone items.
Goal has two, Feature two, Plan three and Phase one per phase. You can remove any of them as the process earns trust.
The Free plan includes 3 workflow templates and this kit has 4, so the full kit needs Pro or above.
Any MCP client connected to ConvOps. Verified clients: Claude Code, Claude (desktop, web, Cowork), OpenAI Codex, ChatGPT, Cursor, OpenCode. Runs that change code need a coding client with your repository checked out.