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.
npx agentmods add skills/agentworkforce/relay/writing-agent-relay-workflowsnpx skills add AgentWorkforce/relay --skill writing-agent-relay-workflowsgit clone --depth 1 https://github.com/AgentWorkforce/relayWrote 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.
[](https://agentmods.dev/skills/agentworkforce/relay/writing-agent-relay-workflows)<a href="https://agentmods.dev/skills/agentworkforce/relay/writing-agent-relay-workflows"><img src="https://agentmods.dev/badge/skills/agentworkforce/relay/writing-agent-relay-workflows.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00092 | $0.16543 |
| Opus 5 | $0.00046 | $0.08271 |
| Sonnet 5 | $0.00018 | $0.03309 |
| Haiku 4.5 | $0.00009 | $0.01654 |
Grade A, and why
writing-agent-relay-workflows 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.
How it starts
The opening of the file, as written. The whole thing — 1,524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The @relayflows/core workflow system orchestrates multiple AI agents (Claude, Codex, Gemini, Aider, Goose) through typed DAG-based workflows. Workflows can be written in TypeScript (preferred), Python, or YAML.
Language preference: TypeScript > Python > YAML. Use TypeScript unless the project is Python-only or a simple config-driven workflow suits YAML.
Pattern selection: Do not default to dag blindly. If the job needs a different swarm/workflow type, consult the choosing-swarm-patterns skill when available and select the pattern that best matches the coordination problem.
When to Use
- Building multi-agent workflows with step dependencies
- Orchestrating different AI CLIs (claude, codex, gemini, aider, goose)
- Creating DAG, pipeline, fan-out, or other swarm patterns
- Needing verification gates, retries, or step output chaining
- Designing product-contract workflows where failing checks should route to agents for repair instead of stopping the run
- Dynamic channel management: agents joining/leaving/muting channels mid-workflow
Non-Negotiable Workflow Checklist
Every generated workflow should satisfy this checklist before it is considered complete:
- Start with a deterministic, resumable preflight for repository state, credentials, and declared write scope.
- Pick the coordination shape deliberately: Conversation for non-trivial coordination, Pipeline only for linear one-shot handoffs.
- Use repairable validation gates: capture red output with
failOnError: false, hand it to a repair owner, then rerun the same check. - Run the mandatory fresh-eyes loops in order: Claude review/fix/final review/final fix, then Codex review/fix/final review/final fix.
- Require review fixers to add or update appropriate tests, fixtures, assertions, or deterministic proofs for testable findings.
- Run final deterministic acceptance after the Codex loop and before commit, PR creation, or handoff.
- If a real blocker remains, write
BLOCKED_NO_COMMITwith exact evidence and skip commit/PR creation instead of crashing the workflow. - If the workflow owns shipping, model branch, commit, push, PR creation, and PR URL verification as explicit deterministic steps.
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.
- 5d ago First seen · 1,524 lines · 92 tokens per session scan A 61b3cb5d500e
writing-agent-relay-workflows is a skill published in the GitHub repository AgentWorkforce/relay (813 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 16,543 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
lime-governance
Govern Lime legacy cleanup, fact-source convergence, current/compat/deprecated/dead classification, and guardrails.
lime-quality-workflow
Choose Lime validation commands for GUI, command/bridge, config, version, and PR-readiness changes.
lime-release-workflow
准备并执行 Lime 发版；覆盖版本号、发布说明、产物清理、验证门禁、commit、tag 和推送。.
image_generate
Skill "image_generate" from limecloud/lime, covering 工作目标, 执行规则 and 输出规则（固定）.
brand-persona-knowledge-builder
将品牌定位、价值观、受众画像、语气风格、内容样例、危机回应和表达禁区，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的品牌人设知识库。适用于用户要求“整理品牌人设”“沉淀品牌口吻”“把品牌资料变成可复用语气库”“维护品牌 persona pack”的场景。.
brand-product-knowledge-builder
将品牌产品资料、规格参数、卖点证据、FAQ、价格权益、竞品区别和合规边界，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的产品资料知识库。适用于用户要求“整理产品知识库”“沉淀产品 FAQ”“把品牌产品资料变成项目资料”“维护产品资料包”的场景。.