agent-chaining

agent-chaining is a skill for Claude Code, Codex from giggsoinc/raven. It costs 50 tokens per session (1,028 once invoked), scanned A, original, MIT.

A guide for coordinating multiple coding agents, where separate agents handle parts of a larger task. It covers how they pass information, run in sequence or in parallel, and share useful state.

In plain words
What is it for?
Use it to design or review agent workflows, choose parallel or sequential execution, write complete prompts for subagents, delegate tools, and plan memory or context sharing.
Why use it?
It helps decide when multiple agents are justified and reduces problems caused by missing context, unnecessary cost, delays, or failed handoffs.

Skill for Claude CodeCodex

Part of the raven plugin — 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

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/giggsoinc/raven/agent-chaining
Any agent
npx skills add giggsoinc/raven --skill agent-chaining
Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Made for: Claude Code, Codex.

Or install raven, the plugin that ships this one along with the rest of its 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-chaining

README.md
[![agentmods](https://agentmods.dev/badge/skills/giggsoinc/raven/agent-chaining.svg)](https://agentmods.dev/skills/giggsoinc/raven/agent-chaining)
Your own site
<a href="https://agentmods.dev/skills/giggsoinc/raven/agent-chaining"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/agent-chaining.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,028 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 $0.00050 $0.01028
Opus 5 $0.00025 $0.00514
Sonnet 5 $0.00010 $0.00206
Haiku 4.5 $0.00005 $0.00103

Measured 5d ago against content hash f5f677ab75a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-chaining 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 5d 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.

core/skills/agent-chaining/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Chaining Specialist

Domain: Multi-Agent Systems · Orchestration · Context Management · Subagent Design


Pre-flight — ask before designing any chain

  1. What problem actually requires multiple agents? → single agent first, always
  2. Sequential or parallel? → depends on step dependencies
  3. What's the token budget? → each subagent call costs tokens
  4. What are the failure modes? → what happens if a subagent fails mid-chain?
  5. Where does shared state live? → agents don't share memory

Rule: If one agent with the right tools can do it → don't chain. Chaining adds latency, cost, and failure surface. Justify it.


When to chain vs not

Chain when... Don't chain when...
Work can run in parallel Single-domain task
Specialist isolation needed Tightly sequential, no parallelism
Context window exceeded Shared mutable state needed
Independent verification needed Low latency requirement
Long-running background work You're adding complexity for no gain

Spawning — the critical rules

Subagent has NO memory of the parent conversation. The prompt must be fully self-contained.

Every subagent prompt must include:

  1. Goal in the first sentence
  2. Absolute file paths — no relative references
  3. What you've already done / ruled out
  4. Expected output form
  5. Scope cap — "only look at src/api/, not tests/"
  6. Failure instruction — "if X not found, report that, don't guess"

Parallel: send multiple agent calls in a single message — they run concurrently. Never send independent agents sequentially — doubles latency for no reason.

Background: for long-running tasks where the parent has other work to do. Parent continues; notified when subagent completes.


Context passing — 3 patterns

  • Self-contained prompt — include all context inline. Best default.
  • File handoff — orchestrator writes to a temp file; subagent reads it. Good for large context. Bad for parallel agents that might conflict.
  • Summary handoff — orchestrator compresses Phase 1; subagent gets the summary. Good for sequential chains.

Read the full file on GitHub · 135 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. 5d ago First seen · 135 lines · 50 tokens per session scan A f5f677ab75a6

Subscribe to this mod's changes

agent-chaining is a skill published in the GitHub repository giggsoinc/raven (5 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 1,028 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens