spawn-implementation-agents

A guide for dividing implementation work between a main coding agent and specialized subagents. Subagents are separate agents that handle focused research or verification tasks.

In plain words
What is it for?
Planning multi-phase implementation work, finding codebase patterns, analyzing architecture, writing tests, and running verification with subagents.
Why use it?
Large implementation tasks can consume the main agent’s context, the working space for code and instructions. Delegating analysis and checks leaves the main agent more room to coordinate and write code.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/eveld/claude/spawn-implementation-agents
Any agent
npx skills add eveld/claude --skill spawn-implementation-agents
Clone the repo
git clone --depth 1 https://github.com/eveld/claude

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,085 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01085
Opus 5 $0.00010 $0.00543
Sonnet 5 $0.00004 $0.00217
Haiku 4.5 $0.00002 $0.00109

Measured 2d ago against content hash c3667602fa5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spawn-implementation-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/spawn-implementation-agents/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

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:

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.")

Read the full file on GitHub · 138 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 138 lines · 19 tokens per session scan A c3667602fa5e

Subscribe to this mod's changes

spawn-implementation-agents is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 1,085 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

code-indexing-pipeline

How Infigraph turns source into a graph — adding a language (tree-sitter vs ANTLR grammar-plugin), cross-file call resolution, SCIP compiler-grade enrichment, and file-watch/reindex triage. Use when adding language support, debugging unresolved calls or SCIP import, or triaging stale index/watcher issues.

intuit/infigraph · 70 tokens

review-pr-against-issue

Review one or more PRs against the GitHub issue(s) they claim to fix, including fetching PR branches directly when gh can't reach github.com (e.g. gh is authenticated to an enterprise host instead). Use whenever asked "does this PR fix issue.

intuit/infigraph · 61 tokens

analysis-subsystems

How Infigraph's multi-repo/group mode and taint analysis work internally — HTTP contract extraction heuristics, cross-service edge linking, combined-graph merge, remote mode, plus taint's line-based tracking and sanitizer heuristic. Use when working on crates/infigraph-core/src/multi/ or src/taint/, or investigating…

intuit/infigraph · 80 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens