spawn-implementation-agents

Included with Lifetime

$97 forever

Guide for efficient agent orchestration during implementation to conserve main agent context

AI Agents

What this skill does


# Spawn Implementation Agents

Orchestrate specialized agents during implementation to keep main agent context under 40k tokens per phase.

## The Problem

Without agents, implementing a phase uses ~92k tokens in main agent:
- Read plan & changelog: 15k
- Read existing code files: 30k
- Find usage patterns: 15k
- Write implementation: 10k
- Write tests: 10k
- Run verification: 10k
- Update changelog: 2k

This approaches the 200k context limit and risks compaction.

## The Solution

Use agents to isolate heavy operations:
- Main agent: 38k tokens (plan + changelog + summaries + code writing)
- Sub-agents: 60k tokens total (in isolated contexts)
- Total system: 98k tokens (50% safety margin)

## 5-Phase Orchestration Pattern

### Phase 1: Analysis (Parallel)

Spawn simultaneously to gather context:

```markdown
Task(subagent_type="workflows:codebase-analyzer",
     prompt="Analyze existing auth system architecture.
     Focus on handler pattern, middleware usage, error handling.
     Return 2-3k summary with key patterns and file:line references.")

Task(subagent_type="workflows:codebase-pattern-finder",
     prompt="Find similar implementations of authentication handlers.
     Return 3k of concrete examples showing handler pattern, validation, errors.")

Task(subagent_type="workflows:thoughts-analyzer",
     prompt="Extract insights from changelog.md about previous phase learnings.
     Return 2k of key deviations and discoveries that affect this phase.")
```

**Wait for all three**. Main agent receives ~8k of summaries.

### Phase 2: Implementation (Main Agent)

Main agent writes code using summaries:
- Has patterns from codebase-pattern-finder
- Understands architecture from codebase-analyzer
- Knows previous deviations from thoughts-analyzer
- Writes implementation: 10k tokens
- Total so far: 15k (plan/changelog) + 8k (summaries) + 10k (code) = 33k

### Phase 3: Testing (Sequential)

Spawn test writer:

```markdown
Task(subagent_type="workflows:test-writer",
     prompt="Generate tests for AuthHandler following patterns in testing.md.
     Test functions: Login(), Logout(), ValidateToken().
     Return test code only, ~3k tokens.")
```

Main agent receives test code, integrates it. Total: 36k

### Phase 4: Verification (Sequential)

Spawn verifier:

```markdown
Task(subagent_type="Bash",
     prompt="Run verification commands from plan.md:
     - make test
     - make lint
     - make build
     Return concise summary: ✅ passed or ❌ failed with key errors only.")
```

Main agent receives pass/fail + errors. Total: 38k

### Phase 5: Documentation (Main Agent)

Update changelog.md: 2k tokens. Final total: 40k

## Token Budget Comparison

| Activity | Without Agents | With Agents | Savings |
|----------|----------------|-------------|---------|
| Read plan & changelog | 15k | 15k | 0k |
| Understand existing code | 30k | 3k | **27k** |
| Find patterns | 15k | 3k | **12k** |
| Write implementation | 10k | 10k | 0k |
| Write tests | 10k | 3k | **7k** |
| Run verification | 10k | 2k | **8k** |
| Update changelog | 2k | 2k | 0k |
| **TOTAL** | **92k** | **40k** | **52k** |

## Guidelines

**When to spawn in parallel**:
- Analysis phase (codebase-analyzer + pattern-finder + thoughts-analyzer)
- Independent lookups (finding multiple unrelated examples)
- Reading multiple unrelated files

**When to spawn sequentially**:
- Test writing (needs implementation to be done first)
- Verification (needs tests to be written first)
- Operations that depend on previous results

**What agents return**:
- **Summaries**, not raw data (2-5k tokens each)
- **Key patterns**, not all files (concrete examples only)
- **Pass/fail + errors**, not full output (1-2k tokens)

## Benefits

- **60% token reduction** per phase in main agent
- **Larger phases possible**: 5-8 files instead of 3-5
- **Complex integrations supported**: Agents find patterns
- **Large files OK**: Agents handle reading (>2000 lines)
- **Safety margin**: 100k tokens remaining in system

## Important Notes

- Main agent NEVER reads large files directly
- Main agent orchestrates, sub-agents execute
- Summaries are compressed, not exhaustive
- This is guidance, not automation - user still in control

Files: 1

Size: 4.3 KB

Complexity: 7/100

Category: AI Agents

Source: https://github.com/eveld/claude/tree/main/skills/spawn-implementation-agents

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts