What is holix-subagents?

A guide for managing subagents through their full lifecycle, from starting background workers to collecting results and answering their questions.

Delegating research, coding, analysis, reviews, and other background tasks to specialized subagents or external coding tools.

It keeps delegated work organized while the main conversation continues.

holix-subagents — Skill for Claude Code by javded-itres

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.

Any agent

npx skills add javded-itres/Holix --skill holix-subagents

Clone the repo

git clone --depth 1 https://github.com/javded-itres/Holix

Made for: Claude Code.

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/javded-itres/holix/holix-subagents/github.svg)](https://agentmods.dev/skills/javded-itres/holix/holix-subagents)

Your own site

<a href="https://agentmods.dev/skills/javded-itres/holix/holix-subagents"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-subagents/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/javded-itres/holix/holix-subagents"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-subagents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,394 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00095	$0.02394
Opus 5	$0.00048	$0.01197
Sonnet 5	$0.00019	$0.00479
Haiku 4.5	$0.00010	$0.00239

Measured 4d ago against content hash 2ba63a499d64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

holix-subagents 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 4d 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/bundled/holix-subagents/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

The user wants background specialized work without blocking the main Holix chat:

research, coding, review, writing, analysis
optional: hand off implementation to external coding CLIs (Claude Code, OpenCode, Grok Build) via an assigned coder sub-agent

Use sub-agents only when the user asks to delegate (/subagent-spawn, "запусти субагента", etc.), except site/resource analysis with many real links from fetch_url — then call research_site_pages (it spawns page_analyst workers). Do not auto-spawn other types for regular chat questions.

Prerequisites

Enabled (default on): enable_subagents: true in profile config.yaml or HOLIX_ENABLE_SUBAGENTS=true.
Profile active: holix --profile <name> … or HOLIX_PROFILE.
Limits (profile config.yaml):
- subagent_max_concurrent (default 4)
- subagent_process_timeout (seconds per job)
- subagent_default_process_mode: process (Linux/macOS, isolated) or async (in-process)

If spawn fails with "disabled" → tell user to enable sub-agents and retry.

Built-in types

Type	Use for
`researcher`	Deep research, files + web
`web_researcher`	Web search + synthesis
`page_analyst`	One page of a site (`fetch_url` only; spawned by `research_site_pages`)
`coder`	Code write/edit/debug, terminal, tests
`analyst`	SQL, data, calculations
`reviewer`	Code review
`writer`	Docs and content

Custom types: profile subagents/types.json, managed in TUI /subagent-types or listed with /subagent-types list.

Duplicate active jobs get suffixed ids: coder-2, coder-3, …

Two ways to start work

A. Main agent (recommended for natural language)

User asks in chat; you (main agent) use tools:

delegate_to_subagent(agent_type, task) → returns job_id
Optionally list_subagents to check status
wait_subagent_result(job_id) when the answer must be included in your reply
terminate_subagent(job_id) to cancel

Read the full file on GitHub · 293 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.

4d ago Changed · +6 lines 2ba63a499d64
8d ago First seen · 287 lines · 95 tokens per session scan A d7b6b93fc902

Subscribe to this mod's changes

holix-subagents is a skill published in the GitHub repository javded-itres/Holix (14 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,394 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.

Building agents Claude Code agent-skills ai assistant background delegate external-cli holix launch spawn sub-agent subagents

magazine-web-ppt

For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.

nexu-io/open-design · 67 tokens

holix-subagents

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

When to use

Prerequisites

Built-in types

Two ways to start work

A. Main agent (recommended for natural language)

What this file has done since we first saw it

Other skills, from other repositories

magazine-web-ppt

html-ppt-zhangzara-coral

google-drive-sheets

interactive-login

slack-drafts

connect-apps