agentsclimarketplace

Role baton orchestrator

Skill chf3198/megingjord-harness/skills/role-baton-orchestrator

AI agent governance harness: baton workflow, fleet LLM routing (Ollama/Claude/OpenRouter), and CI gates for Copilot, Claude Code, and Codex.

Install
npx -y skills add chf3198/megingjord-harness --skill role-baton-orchestrator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Orchestrate single-thread baton handoff across Manager -> Collaborator -> Admin -> Consultant with explicit entry/exit contracts.

SKILL.md

3.0 KB, 579 tokens by cl100k_base, as published. Nobody here has run it

Role Baton Orchestrator

Purpose

Provide deterministic role sequencing for end-to-end tasks while preventing overlap and instruction drift.

Sequence (fixed, per ticket)

  1. Manager
  2. Collaborator
  3. Admin
  4. Consultant

Only one role may be active per ticket at a time. Multiple tickets may have different active roles concurrently.

Parallel dispatch

Manager may hand off N tickets to N different collaborators simultaneously. Each ticket carries its own baton independently. Constraints:

  • Each collaborator owns exactly one ticket at a time.
  • Admin merges are serialized (one PR at a time) to avoid conflicts.
  • Collaborators pull latest main before creating PR.

Research ticket lifecycle

Research tickets skip branch/PR/merge. Baton sequence:

  1. Manager: scope research question, assign collaborator (fleet LLM).
  2. Collaborator: produce research, post findings on ticket.
  3. Admin: review storage placement (wiki/research/), no merge.
  4. Consultant: validate quality, close ticket.

Entry criteria

  • Manager: task goal known.
  • Collaborator: manager handoff exists.
  • Admin: collaborator validation evidence exists.
  • Consultant: admin execution evidence exists (or explicit N/A).

Stop conditions

  • Missing required handoff artifact for next role.
  • Contradictory constraints between role outputs.
  • Failed mandatory gate without remediation path.

Handoff artifacts

  • Manager -> Collaborator: scope, constraints, acceptance criteria, gate checklist.
  • Collaborator -> Admin: changed surfaces + validation evidence.
  • Admin -> Consultant: operational outcomes + governance/release status.
  • Consultant -> Finish: risks, confidence, follow-up recommendations.

Required references

  • repo-standards-router for standards/gates.
  • workflow-self-anneal only for post-failure/process drift.
  • Domain skills for specialized checks (release/docs/security/profile).

Consultant rating rubric (quick)

  • 5: contract present but ambiguous; handoffs not reliably testable.
  • 7: clear contracts; occasional ambiguity in escalation boundaries.
  • 9: deterministic handoffs, explicit stop conditions, evidence-complete transitions.
  • 10: same as 9 plus stable multi-session consistency with zero overlap drift.

Output format

ROLE_BATON_REPORT
context: <new-task|post-failure|pre-merge|pre-release>
scope: <code|ops|governance|mixed>

manager_handoff:
- scope:
- constraints:
- acceptance:
- gates:

collaborator_handoff:
- implementation_summary:
- validation_evidence:

admin_handoff:
- operations_executed:
- governance_status:

consultant_closeout:
- independent_findings:
- residual_risks:
- confidence: <low|medium|high>
- follow_ups:

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most agent orchestration skills give in 579 tokens

Counted across 742 of the 995 authors here whose files we hold, read 2026-08-07

  • Reference existing artifacts by path or URLin 53 of 742, across 25 files
  • Run the full test suite after integrating changesin 51 of 742, across 19 files
  • Dispatch one agent per independent problem domainin 50 of 742, across 17 files
  • Verify fixes do not conflictin 45 of 742, across 13 files
  • Include a suggested skills section in the documentin 45 of 742, across 17 files
  • Redact sensitive informationin 41 of 742, across 11 files
  • Save to the temporary directory of the operating systemin 39 of 742, across 10 files
  • Tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
  • Spot check agent changes for systematic errorsin 34 of 742, across 7 files
  • Write a handoff document summarising the current conversationin 31 of 742, across 6 files
  • Assign each agent a specific scopein 23 of 742, across 8 files
  • Provide specific scope and clear goalin 23 of 742, across 5 files

Said here and by no other author read

  • execute roles in fixed sequence per ticket
  • keep only one role active per ticket
  • assign each collaborator exactly one ticket
  • serialize admin merges to avoid conflicts
  • pull latest main before creating a pull request
  • skip branch pull request and merge for research tickets

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.