cc-launch-workflows

A Claude Code workflow launcher that starts executing an approved plan only after the user asks for execution.

In plain words
What is it for?
Use it to turn a completed conversation plan into background implementation work, launching exploration workers first when important context is missing.
Why use it?
It separates planning from implementation and uses fresh worker sessions, which helps carry out a plan with clear orchestration and the required model choice.

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/dotlas/skills/cc-launch-workflows
Any agent
npx skills add dotlas/skills --skill cc-launch-workflows
Clone the repo
git clone --depth 1 https://github.com/dotlas/skills

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,035 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 $0.00037 $0.01035
Opus 5 $0.00018 $0.00517
Sonnet 5 $0.00007 $0.00207
Haiku 4.5 $0.00004 $0.00103

Measured 2d ago against content hash 8c36b5e8779c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-launch-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 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/custom/common/cc-launch-workflows/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

After planning is complete and the user asks to execute, launch the plan as a background workflow of fresh Sonnet worker subagents, with the current agent (you) as orchestrator. If you do not have necessary context, you must launch “Explore” subagents to gather the required information before launching the workflow.

Ultracode: create a workflow based on the current active conversation’s plan. You are the manager / orchestrator and the subagents of the workflow are the workers.

Key Attributes of the workflow declaration:

  • The model used for implementation must be Sonnet only, for every worker. If you cannot guarantee Sonnet, you must resolve this with the user. Every agent() call in the workflow script must pass { model: 'sonnet' } explicitly. The Workflow tool defaults each worker to the planning session’s model, so workers silently inherit that expensive model unless you override. This is the one place you deliberately ignore the default workflow tool’s “omit model” preset. Set an appropriate effort too. Look at the effort matrix below to decide per-worker effort levels.
Worker Effort Type of Problem Example Use-Cases
medium Pure mechanical changes. File locations, what code to add or change are all resolved already, and its just low cognitive effort to implement. Add a new utility function, refactor a function, add a parameter to an endpoint, etc. When the worker doesn’t see more than 10 or so simple / small files.
high Lower mechanical, higher cognitive load when making changes or adding code. Adding a new endpoint, adding a new feature, creating a new table, etc. When the worker needs to know how the codebase is strung up so that it doesn’t trip any wiring.
xhigh Mission critical workloads, or highly cognitive code changes that require presence and mindfulness. Adding a new page, building a new notebook or subdir, adding code for authentication or authrorization / security workloads, etc. When the worker needs to seriously consider surfaces and blast radius without causing regressions.
  • The context must be fresh for each worker, and only relevant context should be passed to launch each worker. Common information that is required for all workers can be passed as a shared context or through a common file on disk.
  • If each worker starts with needing to build context itself again, the prompt and context injected is not complete enough.

Read the full file on GitHub · 75 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 · 75 lines · 37 tokens per session scan A 8c36b5e8779c

Subscribe to this mod's changes

cc-launch-workflows is a skill published in the GitHub repository dotlas/skills (2 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 1,035 once invoked, about $0.0002 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

erpaval

Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…

theagenticguy/erpaval · 174 tokens

product-discovery

File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…

theagenticguy/erpaval · 242 tokens

agent-ux-patterns

Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use…

theagenticguy/erpaval · 182 tokens

meta-prompt-optimizer

Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude…

theagenticguy/erpaval · 230 tokens

product-strategy

File-first orchestrator for business and product strategy frameworks. Frames the challenge with a CPO / CSO / VP Design role, spawns parallel framework agents (Rumelt kernel + Crux, Wardley Maps, Minto Pyramid as thinking structure, Working Backwards PR-FAQ as discovery artifact), synthesizes outputs into one strategy…

theagenticguy/erpaval · 216 tokens

tech-stack-builder

Opinionated tech stack recommendations and settled library references. Two modes: (1) /build-stack runs parallel researcher agents to compare candidates and emit a stack report + ADRs for greenfield projects; (2) direct reference routing for coding with settled defaults. Use when the user asks to recommend a stack…

theagenticguy/erpaval · 274 tokens