A guide for building multi-agent AI workflows, where separate AI workers handle steps under a fixed controller. It covers both code-focused engineers and people describing an outcome in plain language.

Use it to design or repair agent systems, bots, pipelines, and swarms. It helps structure workflows with saved progress, repeatable routing, focused handoffs, and run logs.

It helps make multi-step AI tasks predictable, recoverable after failures, and safe to retry. It also limits what each worker receives and records each step.

graphsmith — Skill for Claude Code and Codex by SathiaAI

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/SathiaAI/graphsmith

agentmods

npx agentmods add skills/sathiaai/graphsmith/mcp-server

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sathiaai/graphsmith/mcp-server/github.svg)](https://agentmods.dev/skills/sathiaai/graphsmith/mcp-server)

Your own site

<a href="https://agentmods.dev/skills/sathiaai/graphsmith/mcp-server"><img src="https://agentmods.dev/badge/skills/sathiaai/graphsmith/mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sathiaai/graphsmith/mcp-server"><img src="https://agentmods.dev/badge/skills/sathiaai/graphsmith/mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,576 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00204	$0.02576
Opus 5.5	$0.00082	$0.01030
Sonnet 5.5	$0.00041	$0.00515
Haiku 4.5	$0.00020	$0.00258

Measured 1mo ago against content hash d51861f25bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graphsmith 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 1mo ago.

The scan reads SKILL.md. This mod also ships 15 executable files (bin/graphsmith-mcp.js, src/auth.js, src/httpTransport.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to graphsmith — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

mcp-server/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GraphSmith

Turn a goal into a reliable multi-agent workflow. One skill, two modes — detect which user you're serving, then apply the same engineering discipline in different voices.

The discipline (never negotiable, in either mode):

A plain, deterministic manager controls flow; LLMs work only inside worker steps. Control returns to the manager after every step.
Save after every step — a crashed run resumes, never restarts.
Every step is safe to re-run — assume it WILL be retried.
No clocks or randomness in routing — same inputs, same path.
Minimal handoffs — workers get only what they need.
Grounded claims — anything said about existing code cites KnoSky.
One log line per step — run ID, step, status, duration.

Mode detection (do this first, silently)

Score the context. Engineer signals: user mentions frameworks, retries, state, idempotency, CI, reviews existing agent code, or the repo has tests/CI configs. Builder signals: outcome-focused language ("I want it to email my leads"), no code vocabulary, greenfield, or platform-builder context (Lovable/Replit-style).

Builder mode → plain English only. Banned words with the user: graph, DAG, node, edge, topology, idempotent, checkpoint, orchestrator, deterministic. Use: blueprint, worker, handoff, save point, manager, "safe to re-run."
Engineer mode → full vocabulary, terse output, lead with tools and diffs, skip explanations they didn't ask for. Never talk down.

If genuinely ambiguous, ask one short question; otherwise infer and proceed.

Phase 0 — Ground (KnoSky)

If the task involves an existing repo or docs folder:

Run node scripts/knosky-sync.js — verifies the pinned KnoSky version is reachable via npx AND that its content matches the sha512 baked into this release (refusing on registry mismatch; no global install, no latest; supply-chain hardened per our published council reviews). Non-blocking: offline or registry failures never stop the task. Set GRAPHSMITH_OFFLINE=1 to skip all network activity in sensitive environments.
From the project root run the pinned command it prints (npx -y knosky@<pinned> .) — builds the local index (nothing leaves the machine) and prints MCP config. Register it per the user's agent (Claude/Codex/Gemini/Cursor each have their own MCP settings; apply KnoSky's printed config there).
Cite or flag. Every claim about existing code carries a KnoSky citation (real path). If you can't cite, say "inferring." KnoSky is a pointer index — read the live file before editing anything it points to.

Read the full file on GitHub · 118 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 118 lines · 204 tokens per session scan A d51861f25bcd

Subscribe to this mod's changes

graphsmith is a skill published in the GitHub repository SathiaAI/graphsmith (4 stars, last pushed 18d ago), licensed MIT. It adds 204 tokens to every session and 2,576 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to graphsmith, differing in 0 lines, and is treated as a copy.

Building agents Claude Code agent-skills ai-agents chaos-testing checkpointing codex

Angry User Simulator

Simulate aggressive user behavior patterns including rapid clicking, random navigation, form abuse, tab spamming, and unexpected interaction sequences to find UI resilience issues.

PramodDutta/qaskills · 34 tokens

agent-resilience-testing

Orchestrates end-to-end resilience testing for LLM agents with AgentBreak, including LLM infrastructure failures, prompt injection, agent skill supply-chain risk, guardrail verification, and MCP server/tool failures. Use when the user asks to "test my agent for resilience", "chaos test this agent", "find failure modes…

mnvsk97/agentbreak · 97 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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