agentmods.dev

confighub-lookup

confighub-lookup is a skill for Claude Code from confighub/confighub-skills. It costs 150 tokens per session (2,623 once invoked), scanned A, original, MIT.

A lookup guide for ConfigHub and its `cub` command-line tool. It tells an agent to check the installed tool and current documentation before explaining commands or concepts.

In plain words
What is it for?
Use it when checking ConfigHub login status, reading its overview, learning about entities or functions, or preparing a `cub` command.
Why use it?
ConfigHub and its command options can change, so relying on memory may produce incorrect instructions. This guide reduces that risk by requiring current, version-specific information.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the confighub-skills plugin — 1 skill, 1 hook shipped together

not rated 2repo 21d ago A scan 150 tokens original MIT

Good fit Use it when checking ConfigHub login status, reading its overview, learning about entities or functions, or preparing a cub command.

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

Made for: Claude Code.

Or install confighub-skills, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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 confighub-lookup

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/confighub/confighub-skills/confighub-lookup"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/confighub-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,623 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 $0.00150 $0.02623
Opus 5.5 $0.00060 $0.01049
Sonnet 5.5 $0.00030 $0.00525
Haiku 4.5 $0.00015 $0.00262

Measured 19d ago against content hash 8c1f7349fc5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

confighub-lookup 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 19d 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/confighub-lookup/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

confighub-lookup

ConfigHub changes quickly, and what you remember about it is probably out of date. Look up how the installed version behaves before you explain a concept or compose a command. The help that ships with cub describes the version that is installed; the docs describe the latest release.

Look it up, in this order

  1. Check what is installed and that it can reach the server:

    cub version

    cub auth status

    cub version prints the client version, and the server's when it can reach it. If cub auth status fails, ask the user to log in with cub auth login. It opens a browser, so it is theirs to run.

  2. Read the agent overview once per session. It covers the model, the command shape, output options and the conventions every command shares:

    CONFIGHUB_AGENT=1 cub --help-overview

  3. Read the help of every command before you use it. Do this every time, including for commands you have used before. Flags, defaults and positional arguments change between releases:

    CONFIGHUB_AGENT=1 cub <entity> --help

    CONFIGHUB_AGENT=1 cub <entity> <verb> --help

    CONFIGHUB_AGENT=1 adds the sections written for agents. Run --help on the exact command path you are about to use. Help for the parent command does not describe a subcommand's flags.

  4. Look up entity fields when you need to read or filter on one:

    cub <entity> explain

    cub <entity> explain <Field>

    These describe the fields from the API's own schema. The field names are the ones -o json, -o jq=..., --select and --where use.

  5. Look up functions before you run one. Functions are how configuration data is read, changed and validated:

    cub function list --space <space> --toolchain Kubernetes/YAML

    cub function explain <function> --space <space>

  6. Read the docs for concepts and workflows. The docs are served as raw markdown:

    • https://docs.confighub.com/markdown/index.md lists every page.
    • https://docs.confighub.com/markdown/sitemap.json lists them with titles and sizes.
    • Each page is at https://docs.confighub.com/markdown/<path>.md.

Read the full file on GitHub · 186 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. 19d ago First seen · 186 lines · 150 tokens per session scan A 8c1f7349fc5d

Subscribe to this mod's changes

confighub-lookup is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 150 tokens to every session and 2,623 once invoked, about $0.0006 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 2026-10-19.

Related

confighub-lookup compared with skills from other repositories

confighub-lookup next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
confighub-lookupconfighub/confighub-skillsSkill221d agoMITA150Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex