agentmods.dev

skillmux-manage

skillmux-manage is a skill for Claude Code, Codex from klhq/skillmux. It costs 50 tokens per session (986 once invoked), scanned A, original, MIT.

A command-line tool for managing skillmux, including listing skills, checking their status, installing skills from Git repositories, and changing where skills are used.

In plain words
What is it for?
It is for checking installed skills, making skills core or project-scoped, installing or updating them, and reviewing skillmux status.
Why use it?
It provides a controlled way to inspect and change skill configuration instead of editing its files and directories by hand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 2d ago A scan 50 tokens original MIT

Good fit It is for checking installed skills, making skills core or project-scoped, installing or updating them, and reviewing skillmux status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/klhq/skillmux/skillmux-manage
View source ↗ klhq/skillmux
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 klhq/skillmux --skill skillmux-manage
Clone the repo
git clone --depth 1 https://github.com/klhq/skillmux

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.

agentmods badge for skillmux-manage

README.md
[![agentmods](https://agentmods.dev/badge/skills/klhq/skillmux/skillmux-manage/github.svg)](https://agentmods.dev/skills/klhq/skillmux/skillmux-manage)
Your own site
<a href="https://agentmods.dev/skills/klhq/skillmux/skillmux-manage"><img src="https://agentmods.dev/badge/skills/klhq/skillmux/skillmux-manage/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.

agentmods 80×15 button for skillmux-manage

Your own site · 80×15
<a href="https://agentmods.dev/skills/klhq/skillmux/skillmux-manage"><img src="https://agentmods.dev/badge/skills/klhq/skillmux/skillmux-manage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 986 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 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 5.1 $0.00050 $0.00986
Opus 5.5 $0.00020 $0.00394
Sonnet 5.5 $0.00010 $0.00197
Haiku 4.5 $0.00005 $0.00099

Measured 4d ago against content hash c3d28436d167, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skillmux-manage 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.

src/builtin-skills/skillmux-manage/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managing skillmux

This skill matches skillmux {{version}}. If skillmux --version prints a different version, run skillmux --help --json and trust its output over this text.

Ground rules

  1. Pass --json to every command and read the data field of the result. A failure has ok: false and an error.code; USAGE_ERROR means the arguments were wrong, and error.message shows the usage.
  2. Before any command that writes, run it once with --dry-run and show the user what would change.
  3. Pass --yes only after the user has confirmed that change. Never add it on your own to get past a prompt.
  4. Do not edit skillmux.toml, config.toml, or agent skill directories by hand. The commands below keep them consistent.
  5. To learn which commands exist and which ones write, run skillmux --help --json. Each command lists its flags, its subcommands, and writes or writing_subcommands.

Look before you change anything

  • skillmux status --json shows the vault, core usage against its limit, each agent's skill directory, and any problem that needs fixing.
  • skillmux skill list --json lists every skill with its description and placement. The placement is core (every agent sees it), project (only the groups in project_groups), or mcp-only (found through resolve_skill and fetch_skill).
  • skillmux skill list --placement core --json filters to one placement.
  • skillmux skill which <skill_id> --json shows which vault root serves a skill and which roots it shadows.
  • skillmux project list --json and skillmux agent list --json show project groups and configured agents.
  • skillmux doctor --json runs the deeper health checks.

Common tasks

Make a skill core. Core skills load into every session, so each one costs context. Check status first: core.count must stay below core.limit.

skillmux core pin <skill_id> --dry-run --json
skillmux core pin <skill_id> --yes --json

Remove a skill from core with skillmux core unpin <skill_id>. It goes back to mcp-only and stays reachable through resolve_skill.

Read the full file on GitHub · 79 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. 4d ago First seen · 79 lines · 50 tokens per session scan A c3d28436d167

Subscribe to this mod's changes

skillmux-manage is a skill published in the GitHub repository klhq/skillmux (2 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 986 once invoked, about $0.0002 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 2026-11-02.

Productivityagent-skillsdeveloper-toolsmcpmodel-context-protocolsemantic-searchskill-routing
Related

skillmux-manage compared with skills from other repositories

skillmux-manage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skillmux-manageklhq/skillmuxSkill22d agoMITA50Claude Code, Codex
rag-code-reviewlyonzin/knowledge-ragSkill302todayMITA83Claude Code, Codex
email-formattingprovos/ironcurtainSkill6402d agoApache-2.0A53Claude Code, Codex
json-schema-emailsprovos/ironcurtainSkill6402d agoApache-2.0A62Claude Code, Codex
disk-cleanupmtarcure/claude-vibe-squadSkill2289d agoMITA92Claude Code
compact-nowmtarcure/claude-vibe-squadSkill2289d agoMITA82Claude Code
cortex-profilecdeust/CortexSkill76todayMITA98Claude Code