dispatching-coding-agents

A way to send short-lived coding agents to investigate or implement parts of a difficult task using Claude Code or Codex. These agents start without memory of the current conversation, so they need the relevant context supplied to them.

In plain words
What is it for?
Delegating focused code tracing, research, reviews or implementation tasks to Claude Code or Codex agents, including parallel work on separate parts of a problem.
Why use it?
It provides a second opinion or lets multiple investigations run at once when one agent is stuck or a problem is too large for one line of inquiry.

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/letta-ai/letta-code/dispatching-coding-agents
Any agent
npx skills add letta-ai/letta-code --skill dispatching-coding-agents
Clone the repo
git clone --depth 1 https://github.com/letta-ai/letta-code

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,915 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 $0.00000 $0.02915
Opus 5 $0.00000 $0.01458
Sonnet 5 $0.00000 $0.00583
Haiku 4.5 $0.00000 $0.00292

Measured 2d ago against content hash 477fb6d99c37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dispatching-coding-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.

src/skills/builtin/dispatching-coding-agents/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatching Coding Agents

You can shell out to Claude Code (claude) and Codex (codex) as stateless sub-agents via Bash. They have filesystem and tool access (scope depends on sandbox/approval settings) but zero memory — every session starts from scratch.

Default to run_in_background: true on the Bash call so you can keep working while they run. Check results later with TaskOutput. Don't sit idle waiting for a subagent.

The Core Mental Model

Claude Code and Codex are highly optimized coding agents, but are re-born with each new session. Think of them like a brilliant intern that showed up today. Provide them with the right instructions and context to help them succeed and avoid having to re-learn things that you've learned.

You are the experienced manager with persistent memory of the user's preferences, the codebase, past decisions, and hard-won lessons. Give them context, not a plan. They won't know anything you don't tell them:

  • Specific task: Be precise about what you need — not "look into the auth system" but "trace the request flow from the messages endpoint through to the LLM call, cite files and line numbers."
  • File paths and architecture: Tell them exactly where to look and how pieces connect. They will wander aimlessly without this.
  • Preferences and constraints: Code style, error handling patterns, things the user has corrected you on. Save them from making mistakes you already learned from.
  • What you've already tried: If you're dispatching because you're stuck, this prevents them from rediscovering your dead ends.

If a subagent needs clarification or asks a question, respond in the same session (see Session Resumption below) — don't start a new session or you'll lose the conversation context.

When to Dispatch (and When Not To)

Dispatch for:

  • Hard debugging — you've been looping on a problem and need fresh eyes
  • Second opinions — you want validation before a risky change
  • Parallel research — investigate multiple hypotheses simultaneously
  • Large-scope investigation — tracing a flow across many files in an unfamiliar area
  • Code review — have another agent review your diff or plan

Read the full file on GitHub · 233 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 · 233 lines · 0 tokens per session scan A 477fb6d99c37

Subscribe to this mod's changes

dispatching-coding-agents is a skill published in the GitHub repository letta-ai/letta-code (3,178 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,915 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

kungfu-agent-onboarding

Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.

kungfu-systems/kungfu · 32 tokens

moltbook

Participate in Moltbook — the social network for AI agents. Post dream insights, share learned skills, engage in submolt discussions, and build reputation. Use when your human asks you to post on Moltbook, check the feed, or interact with the agent community. Also used during heartbeats for periodic social engagement.

Bitterbot-AI/bitterbot-desktop · 71 tokens

kayba-stage-3-metrics

Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful. Trigger when the user says "run stage 3", "define metrics", "build metrics", "compute baselines", or when invoked by the kayba-pipeline orchestrator. Requires…

kayba-ai/agentic-context-engine · 92 tokens

memory-to-skill

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…

zilliztech/memsearch · 82 tokens

kayba-pipeline

End-to-end agent evaluation and improvement pipeline. Takes a traces folder and optional HITL flag, then orchestrates sub-agents through 7 stages — each stage is its own skill invoked by a dedicated sub-agent. Trigger when the user says "run the pipeline", "kayba pipeline", "evaluate and fix", "full eval", "analyze…

kayba-ai/agentic-context-engine · 91 tokens

kayba-stage-2-domain-context

Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.

kayba-ai/agentic-context-engine · 64 tokens