Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Emasoft/claude-plugins-validation/plugin install claude-plugins-validationWrote 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/emasoft/claude-plugins-validation/cpv-create-micro-agents-workflow)<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-create-micro-agents-workflow"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-create-micro-agents-workflow/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.
<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-create-micro-agents-workflow"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-create-micro-agents-workflow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00126 | $0.02274 |
| Opus 5.5 | $0.00050 | $0.00910 |
| Sonnet 5.5 | $0.00025 | $0.00455 |
| Haiku 4.5 | $0.00013 | $0.00227 |
Grade A, and why
cpv-create-micro-agents-workflow 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.
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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cpv-create-micro-agents-workflow
Overview
Builds the ONE-FOR-ALL AGENT architecture: the agent lists every skill it needs BY NAME
in skills: frontmatter — exactly like an ALL-IN-ONE agent — and the ONLY difference is
WHERE a skill runs: each one executes in a separate subagent (a one-skill-agent, minimal
context) instead of in the agent itself. Small context ⇒ the pattern is more likely
"in-distribution" (better training-memory recall) and every turn is cheap.
A skill's content is NEVER copied. The fork is declared IN PLACE in the shared skill's own frontmatter, so there is no private per-agent copy to rot. That single-source-of-truth rule is also the one genuine COST of this architecture — see "Shared-skill safety" below.
Two paths, and they are complementary:
A. AGENT-SCOPED (in place) — convert_agent.py <agent.md> --to one-for-all. Uses that
agent's own skill closure and routing structure; the choice tree lives in the AGENT's body
(a skill cannot declare its own skills: list — that field is agent-only).
B. PLUGIN-WIDE (RLM workflow) — create_micro_agents_workflow.py <plugin>. A thin
launcher agent plus a Workflow-tool coordinator that plans a task into an ordered skill
sequence and spawns a fresh near-empty agent per step. Only ONE agent is created, because
the per-skill micro-agents are spawned dynamically by the Workflow tool rather than
hand-authored one-per-skill.
The three frontmatter facts that decide whether path A works at all
context: forkis the fork mechanism — NOTagent:.agent:only selects WHICH subagent type once fork is already set (Explore/Planadditionally skip CLAUDE.md, which is how "minimal context" is actually achieved). A skill carryingagent:alone does nothing.backgrounddefaults totrue, so a forked skill returns NOTHING inline — its result arrives as a notification. A graph that threads one step's output into the next needsbackground: false(Claude Code v2.1.218+). Without it the steps appear to run and silently deliver nothing downstream.skills:is NOT valid inside a skill (agent-only), so a node cannot carry its own skill list and the choice tree must live in the agent's body.
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 · 160 lines · 126 tokens per session scan A 729d6a639b15
cpv-create-micro-agents-workflow is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 2,274 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
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…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…