planner-orchestration

Solid

Enforce Kandev's single-session, user-controlled model workflow for feature, fix, debug, review, verification, and delivery work.

AI & Automation 502 stars 69 forks Updated today AGPL-3.0

Install

View on GitHub

Quality Score: 87/100

Stars 20%
90
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Single-Session Orchestration The user-started primary conversation owns durable artifacts, integration judgment, and user communication. Platform-provided explorers and other predefined subagents may continue to serve the harness's normal investigation workflow. This skill governs planned implementation delegation, not the platform's general exploration behavior. ## Model Checkpoints The user, not the harness, selects the model. Keep each phase in the primary conversation so the active model, transcript, and costs are visible in one place. 1. **Design checkpoint — strong model.** Use the user's strong model for clarification, codebase investigation, specs, plans, task decomposition, and high-risk design decisions. Default Codex guidance is GPT-5.6 Sol/high. 2. **Implementation checkpoint — user switch.** Once the spec, plan, and task files are ready, summarize their paths and ask the user to switch the main session to the lower-cost implementation model. Default Codex guidance is GPT-5.6 Terra/medium. Do not silently continue on the strong model when the user has asked for a cost-controlled workflow. 3. **Execution checkpoint — lower-cost model.** In the same conversation, read the approved task file, mark it `in_progress`, implement with `/tdd`, run its exact targeted checks, and mark it `done`. Work sequentially through the plan by default. 4. **Escalation checkpoint.** Stop and ask the user to switch back to a stronger model before an ar...

Details

Author
kdlbs
Repository
kdlbs/kandev
Created
6 months ago
Last Updated
today
Language
Go
License
AGPL-3.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

spec-driven-development

Single-session Kandev feature workflow: clarify intent, create durable specs, plans, and task files on a strong model, then implement and verify them after the user switches the main session to a lower-cost model.

502 Updated today
kdlbs
AI & Automation Listed

workflow-orchestrator

Take on a substantial, multi-step effort as a strategic orchestrator — intake the goal, research and plan it solo, execute it through parallel/sequential agent workflows, then personally verify the result end to end. Use this whenever the user wants to tackle something big or ambitious: a large feature, a cross-cutting refactor, a migration, a codebase-wide audit, a "do all of X / sync everything / overhaul Y" task, or any effort that won't fit in one pass and needs to be planned and orchestrated with rigor. Trigger when the user invokes it by name, says things like "orchestrate this / run a workflow / use subagents / plan and build this / take this on end to end," OR simply describes a meaty multi-part task and wants it done thoroughly and efficiently — even if they never say the words "workflow" or "orchestrate." Do NOT use it for small, single-step tasks that one pass handles directly.

1 Updated 1 weeks ago
FarzamMohammadi
AI & Automation Listed

orchestrate

Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable control tower; a reconcile sweep rebuilds from disk. Never merges, marks a PR ready, or auto-chains into /spec-kickoff. --bookkeeping runs the drain + PR reconcile; --watch loops the step.

1 Updated today
inkatze