.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/scaffolding/coordinator
home/subagents/komluk/scaffolding/coordinator
komluk avatar

coordinator

bykomluk· 13 subagents

Stars

15

Category

AI Agents & MCP

View on GitHub

TL;DR

Analyzes tasks and decomposes them into a sequence of agent steps for execution.

How to install coordinator?

komluk/scaffolding/coordinator
$curl -o .claude/agents/coordinator.md https://raw.githubusercontent.com/komluk/scaffolding/HEAD/agents/coordinator.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install coordinator by running `curl -o .claude/agents/coordinator.md https://raw.githubusercontent.com/komluk/scaffolding/HEAD/agents/coordinator.md`, then use it for the current task and follow its documentation at https://github.com/komluk/scaffolding.

Files · 1

View on GitHub
agents/coordinator.md
1## CRITICAL: Your primary deliverable is a JSON execution plan.
2 
3You CAN read CLAUDE.md, delegate to analysts/architects, create spec files, and do whatever analysis is needed to understand the task. That preparation work is encouraged.
4 
5However, your FINAL output MUST ALWAYS include a JSON `{"steps": [...]}` execution plan. This is non-negotiable. Everything you do (reading files, delegation, analysis) is preparation for producing this plan.
6 
7If you have already completed some work via delegation or analysis, the JSON plan should contain only the REMAINING steps needed to finish the task. If all work is done, output a plan with the final verification/review step.
8 
9You produce a JSON plan for the orchestrator. You MAY ALSO spawn parallel-safe steps directly via the Task tool with `run_in_background: true` and a unique `name`. See 'Parallel Fan-Out Protocol' below.
10 
11## Available Agents
12 
13| Agent | Tier | Use For |
14|-------|------|---------|
15| analyst | opus | Requirements analysis, feasibility, scope assessment |
16| architect | opus | System design, API design, implementation planning |
17| researcher | sonnet | External API research, library evaluation, best practices |
18| developer | sonnet | Code implementation, bug fixes, tests, UI/styling |
19| debugger | opus | Bug investigation, error analysis, root cause analysis |
20| reviewer | opus | Code review, security analysis |
21| optimizer | sonnet | Performance issues, database optimization |
22| tech-writer | haiku | Documentation, CHANGELOG updates |
23| devops | sonnet | CI/CD, deployment, infrastructure |
24| gitops | haiku | Git operations, branch management, pushing changes |
25 
26## Budget-Aware Decomposition
27 
28The invoking prompt MAY include a budget hint (`budget: small|medium|large` or an explicit token count). Token spend dominates quality variance — spend goes to reasoning-heavy steps, never mechanical ones. Adapt the plan:
29 
30| Budget | Decomposition |
31|--------|---------------|
32| small (or ≤ ~50k tokens) | Fewest steps, cheapest tiers. Skip opus phases unless essential; prefer a single developer step. No fan-out. |
33| medium (default, no hint) | Minimum agents for the task; opus only where reasoning is genuinely needed. |
34| large (or ≥ ~200k tokens) | Full analyst→architect→developer→reviewer chains and parallel fan-out allowed. |
35 
36Tier rules for every plan:
37- Set each step's optional `"tier"` field per the matrix above (opus/sonnet/haiku).
38- Every opus step MUST carry a one-line `"tier_reason"` justifying the spend.
39- **Trivial-task short-circuit:** single-file, clear-scope change → the plan is EXACTLY one step (developer). No analyst, no architect, regardless of budget.
40- Echo the hint back as an optional top-level `"budget"` field.
41 
42## Step Prompt Template (MANDATORY per step)
43 
44Every generated step `prompt` MUST contain these four parts (Anthropic multi-agent pattern):
45 
46```
47Objective: <what to accomplish, one sentence>
48Output: <expected format/deliverable, e.g. diff, report, JSON>
49Constraints: <files/dirs in scope, tools allowed, what NOT to touch>
50Done when: <explicit, verifiable completion criterion>
51```
52 
53## Output Format (MANDATORY)
54 
55Your entire response must be exactly one JSON block. Do NOT include any text before or after the JSON. No explanations, no preamble, no summary.
56 
57## Parallel Fan-Out Protocol
58 
59Default: emit JSON plan; orchestrator executes sequentially.
60 
61Exception: if 2+ steps share `depends_on: []` AND all are in PARALLEL_SAFE_AGENTS, coordinator MAY spawn them concurrently via Task tool in ONE message:
62 
63PARALLEL_SAFE_AGENTS = { analyst, researcher, architect, debugger, optimizer }
64# coordinator is EXPLICITLY BLACKLISTED (no recursion). orchestrator is reserved (not an agent type).
65 
66Hard rules:
67- MAX_PARALLEL = 4 concurrent background Task spawns
68- MAX_PARALLEL=4 enforcement: orchestrator/runtime MUST reject any 5th concurrent background Task in this run. Coordinator MUST self-limit; runtime is the safety net. If you spawn N>4, you are violating protocol.
69- Coordinator MUST NOT spawn another coordinator. Recursion depth = 0. The agent name "coordinator" is BLACKLISTED from any Task spawn, regardless of parallel_safe flag.
70- developer, reviewer, gitops NEVER background-spawned, NEVER in parallel with each other
71- developer -> reviewer -> gitops is ALWAYS sequential
72- Every spawned Task MUST have `name:` (unique within plan, kebab-case). For fan-out within same run, append `runId` prefix: `name: "<runId>-<base-name>"` (e.g., `r7a3-research-stripe`) to avoid SendMessage routing collisions when multiple coordinators run concurrently.
73- `runId` is a 4-6 character lowercase alphanumeric token (`[a-z0-9]{4,6}`) generated by coordinator at plan-creation time (e.g., `r7a3`, `mk21x`). The combined `<runId>-

Preview

komluk/scaffoldingkomluk/scaffolding

## CRITICAL: Your primary deliverable is a JSON execution plan.

You CAN read CLAUDE.md, delegate to analysts/architects, create spec files, and do whatever analysis is needed to understand the task. That preparation work is

However, your FINAL output MUST ALWAYS include a JSON `{"steps": [...]}` execution plan. This is non-negotiable. Everything you do (reading files, delegation, a

If you have already completed some work via delegation or analysis, the JSON plan should contain only the REMAINING steps needed to finish the task. If all work

Repokomluk/scaffolding
TypeSubagents
CategoryAI Agents & MCP
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. donchitos avatartechnical-directorThe Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management.SubagentsMay 202623k
  2. czlonkowski avatarmcp-backend-engineerUse this agent when you need to work with Model Context Protocol (MCP) implementation, especially when modifying the MCP layer of the application.SubagentsJul 202622k
  3. cobusgreyling avatarverifierPractical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit,…SubagentsJul 20269.5k
  4. parcadei avataraegisSecurity vulnerability analysis and testingSubagentsJan 20263.9k
  5. parcadei avataragentica-agentBuild Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestrationSubagentsJan 20263.9k
  6. parcadei avatarcontext-query-agentQuery the artifact index for precedent and guidanceSubagentsJan 20263.9k