shynlee04/hivemind-plugin/sequential-orchestration
Claude Code and agent skill by shynlee04/hivemind-plugin
- community
Checking that the SKILL.md file is still in the repository.
Safer delegation with sequential task execution, result awaiting, retuning, and boundary enforcement. Ensures unbroken hierarchy chains before any action. Context-first, never act without verified planning.
Install
npx vskill@latest install shynlee04/hivemind-plugin/sequential-orchestrationSKILL.md
Sequential Orchestration Skill
Core Philosophy
SEQUENTIAL IS SAFER. Always prefer sequential over parallel unless:
- Tasks have ZERO file/state overlap
- Tasks have ZERO dependency on each other's output
- Failure of one task does not affect others
The Absolute Gatekeeping Factor
Before ANY action, these conditions MUST be verified:
1. Parent Hierarchy Exists (UNBROKEN LINK)
2. Context Is Pure
3. Planning Is Retrieved
Sequential Delegation Protocol
Step 1: Pre-Delegation Gate
If ANY check fails → STOP, fix before proceeding.
Step 2: Delegate with Explicit Return Format
Step 3: Result Processing & Retuning
Step 4: Boundary Enforcement
The Unbroken Link Principle
A hierarchy chain is UNBROKEN when:
- Trajectory → Tactic → Action all exist
- Each child has a valid parent reference
- Timestamps show reasonable progression (< 2hr gaps)
- Cursor position matches actual work focus
Hierarchical Actions Protocol
Level 1: Trajectory (Strategic Goal)
- Set via
declare_intent({ mode, focus }) - Must exist before ANY tactical work
- Survives compaction (stored in hierarchy.json)
Level 2: Tactic (Implementation Strategy)
- Set via
map_context({ level: "tactic", content }) - Must have parent trajectory
- Groups related actions
Level 3: Action (Specific Task)
- Set via
map_context({ level: "action", content }) - Must have parent tactic
- Represents atomic work unit
Context-First Protocol
NEVER ACT WITHOUT:
- Context Loaded:
- Constraints Known:
- Plan Verified:
- Chain Validated:
Red Flags - STOP Immediately
| Condition | Action | |
|---|---|---|
| No trajectory | declare_intent first | |
| Chain broken | map_context to repair | |
| Drift > 60 | think_back to recover | |
| No plan in memory | Create plan before acting | |
| Domain boundary violation | Reroute to correct domain | |
| Pending failure unacknowledged | Acknowledge and resolve |
Quick Reference Commands
Related Skills
- delegation-intelligence: Decision patterns for parallel vs sequential
- evidence-discipline: Verification requirements for claims
- context-integrity: Context recovery and chain repair
- session-lifecycle: Session state management
Security
- Security scanPassed, 96 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/sequential-orchestration/SKILL.md
Popularity
- Repository stars
- 50
- Repository forks
- 17
- Repository npm downloads, 7 days
- 17
- 7-day trend score
- 33
Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 17 Mar 2026, 7 months ago.
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/shynlee04/hivemind-plugin/sequential-orchestration)