vanillagreencom/kendex/orch
Claude Code and agent skill by vanillagreencom/kendex
- community
Checking that the SKILL.md file is still in the repository.
PRIMARY AGENT ONLY. Load to orchestrate a Linear or GitHub work item from preparation through merge.
Install
npx vskill@latest install vanillagreencom/kendex/orchSKILL.md
Orchestration
Load mailbox for takeover; github, worktree and linear before use. Dev and reviewer skills call orch scripts.
MODE SWITCH: you are the orchestrator. Delegate every implementation, review, and QA task to a specialist sub-agent. Never edit code unless the user explicitly asks, or the item runs themicrotier (workflows/micro.md), whose runner makes the edit itself.
The Cycle
Get the issue → dev implements → publication, review and fixes in the order from pr-order --help → required CI and review gate → merge.
- Bounded loops. A fix round addresses blockers only, and the same pass declines or tracks every
fixsuggestion (workflows/review-pr.md § 4); re-review narrows to the fix diff, the domains it touched, and the class of every defect it fixed (reviewer/SKILL.md § Re-Review Rounds); two consecutive rounds with no new blocker end the review; workflows/review-pr.md § At The Cap sets the cap, cap 0 and a fix round's own regression. - Finding conduct. Apply reviewer's decision flow, recurrence rule and filing bar.
- Scope cuts. A reviewer or orchestrator can choose a cut round. A round whose only findings are scope or wording asks ends the review: reply, resolve, push nothing, merge through the gate.
- Ask gates. Which questions reach the user is references/communication-modes.md; nothing outside that file narrows or widens the set. Use communication for prose under the mode
ORCH_USER_MODEnames. That ask set holds whateverORCH_DECISION_MODEsays. Merge asks unlessORCH_MERGE_AUTONOMY=auto, which merges without asking only when every merge gate is green. In a lane every ask gate islane-mail, never the harness question tool: references/skill-rules.md § Coordination. - Post-PR autonomy. After a PR exists,
ORCH_DECISION_MODE=auto-recommendedtakes and logs the continuing option while a bounded wait, retry, or triage round remains.askpresents the listed choice.workflow-state head-budget takeowns automatic retry spending, starting the count over on a changed head for review-wait only. At a cap,workflow-state post-pr-stop recordatomically persists the named stop and renders its matching Markdown comment; the workflow posts that file to the PR and returns the stored stop. A nested caller usesrecord-if-emptyso a precise upstream stop wins. Every continuing action clears the stop withworkflow-state update. Initialize the resolved state key before these transitions.ORCH_MERGE_AUTONOMYcontrols merge consent only. - The overseer reads results. It accepts green lane checks and CI without reruns, prepare, commit, push or merge grants, or a shared validation slot. Only local micro runs here; its commit chain validates it. Green lanes with user merge consent arm auto-merge and own its wait per
workflows/merge-pr.md. Dev test-only validation-ceiling reports end validation. Lanes tick branch boxes with proving artifacts. It ticks post-merge boxes only after reading proving artifacts at their revision and conditions: test output, screenshot, measured figure or deployed screen. Lane summaries are no proof. A container closes when its last child is Done or Canceled, throughcontainer-close; an outcome to read lives in its own child. When evidence is due or contradicted, it reads it to narrow, replace or stop the failed intervention. A fix item is not the default. It gives no model or account instructions. Lanes keep launch models and launch no lanes. - Item work stays in lanes. A fleet is hosted when
lane-host resolveprints anything exceptlocal. Overseers share its control VM for coordination. The overseer does no item work there: no worktree, item branch, dev, review or fix agent, validation, build, install or test run. Every item round goes to its branch's lane. A control-host subagent (sweep, triage verifier, measurement or research) reads without bulk writes: stream archives, or extract each into its own scratch subdirectory and remove the extraction before the next. Before extraction, read its uncompressed size and the volume's free space; if less than 3 GB would remain, stop and report to the overseer without extracting. No history-wide content read (git log -Sor-G,--all -p, or any command reading every blob): lazy fetch in a partial clone can fill disk. Search viagh search code, the GitHub API, or a lane. No busy waits (/dev/zero,/dev/urandom, spin polls) on the shared host. Wait with one bounded background command and completion notice, or watch events. Every control-host subagent brief includes this rule. Its scratch location is an empty subdirectory (tmp/<run>/<agent-topic>/) only that subagent removes, never one the overseer's background jobs read. Fleet guards read command blocks. Refresh follows the consumer's owner. No--refresh-onlyexception. - Acceptance is artifact-based. A round closes on a validated on-disk artifact plus git/tracker state, never on a return message.
- Rules reload after a rebase. Before a step that can rebase the branch (
worktree-push,worktree create --reuse, a restack), bindgit -C [WT_PATH] rev-parse --verify HEADas[BOUND_HEAD]. A step that moves it is followed at once, before any validation, publication or arm, bygit -C [WT_PATH] diff --no-renames --name-only [BOUND_HEAD] HEAD -- <each loaded file's repo path>and a re-read of each listed file at[WT_PATH]/<path>, with the deleted-path rule of dev SKILL.md § Round Contract. - A lane is quiet.
ORCH_LANE_OUTPUTdecides what a lane prints and where a filled<output_format>block goes: references/skill-rules.md § Lane Output.
Commands
Route <command> [args] to its workflow and follow Workflow Execution.
| Command | Arguments | Workflow | Purpose | |||
|---|---|---|---|---|---|---|
start | [ISSUE_ID] \ | github OWNER/REPO#N | workflows/start.md / workflows/start-worktree.md | Prepare one work item; from a worktree, run the full session | ||
start new | `linear\ | github ...` | workflows/start-new.md | Create one issue, then start it | ||
micro | [ISSUE_ID] \ | github OWNER/REPO#N | workflows/micro.md | Few-line tier: edit, commit, PR, arm, merge, with no dev agent and no review cycle | ||
small | [ISSUE_ID] \ | github OWNER/REPO#N | workflows/small.md | One-subsystem tier: the full session under thin review bounds | ||
handoff | `linear\ | github ...` | workflows/handoff.md | Launch independent sessions | ||
plan-issues | `PLAN_PATH linear\ | github` | workflows/plan-issues.md | Convert plan items into issues | ||
dev-start | [ISSUE_ID] | workflows/dev-start.md | Delegate implementation | |||
dev-fix | [ISSUE_ID] | workflows/dev-fix.md | Delegate fix items | |||
ci-fix | PR_NUMBER \ | queue | workflows/ci-fix.md | Analyze and fix CI failures | ||
review | [all] \ | [last N] \ | [HASH] | workflows/review.md | On-demand review of local changes | |
review-codebase | [PATH] | workflows/review-codebase.md | Whole-codebase fanout, findings only | |||
review-pr | [PR_NUMBER] | workflows/review-pr.md | Review cycle with fixes and QA | |||
review-pr-comments | PR_NUMBER \ | BRANCH | workflows/review-pr-comments.md | Triage PR review comments | ||
submit-pr | [PR_NUMBER] | workflows/submit-pr.md | Push, create PR, gates, merge | |||
merge-pr | PR_NUMBER \ | all | workflows/merge-pr.md | Verify conditions and merge | ||
post-summary | [ISSUE_ID] | workflows/post-summary.md | Post summary and handoff comments | |||
verify | none | workflows/verify.md | Read and complete due verification checks | |||
oversee | none | workflows/oversee.md | Fleet mode: one session per unblocked item, shepherd every PR to merge |
`start` routing. github OWNER/REPO#N → TRACKER=github, ISSUE_ID=issue-N, keep OWNER/REPO for the API; otherwise Linear unless the id starts with issue-. A cwd whose git common dir differs from .git is a worktree → workflows/start-worktree.md; otherwise workflows/start.md.
Scripts
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/orch/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/vanillagreencom/kendex/orch)