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.
npx skills add confighub/confighub-skills --skill confighub-coregit clone --depth 1 https://github.com/confighub/confighub-skillsWrote 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/confighub/confighub-skills/confighub-core)<a href="https://agentmods.dev/skills/confighub/confighub-skills/confighub-core"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/confighub-core/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/confighub/confighub-skills/confighub-core"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/confighub-core.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 | $0.00068 | $0.04724 |
| Opus 5 | $0.00034 | $0.02362 |
| Sonnet 5 | $0.00014 | $0.00945 |
| Haiku 4.5 | $0.00007 | $0.00472 |
Grade A, and why
confighub-core 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.
How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
confighub-core
Execution mode: follow references/execution-modes.md. This Skill grants no automatic tool permission. Route a concrete change to its owning Skill; in standalone use that Skill submits one exact requested write to the host permission system, while an external overlay may impose a stricter stop.
The foundational skill: concepts and routing. It explains ConfigHub's model, carries the doctrine that every other skill assumes (config as data, one resource per Unit, the component model, opt-in protection), and hands the concrete task to the skill that owns it.
Load this first when the intent is broad. Hand off as soon as the task is concrete — the recipes live in the dedicated skills, not here.
When to use
- User is new to ConfigHub or asks for a tour ("how does ConfigHub work?").
- User asks what an entity is or how two relate (Component vs Variant vs Space, Target vs Worker, Trigger vs Filter, upstream vs downstream).
- User is authoring new config and is about to reach for Helm / Kustomize / Jsonnet / a values file — apply the config-as-data rule below, then route.
- User is deciding how to organize Spaces across environments, regions, clusters, or tenants.
- User asks how many Units a pile of resources should become ("one Unit or many?").
- User wants to protect a Space/Unit from accidental delete or destroy, or asks what "protected path" means.
Do not load for
- A task that already has an obvious dedicated skill — route instead (see Routing).
- Deep product-support questions that belong in docs (
https://docs.confighub.com/), not a skill.
Confirm before you compose
Never compose cub commands from memory. Confirm the verb and flags with cub <verb> --help before a read or requested mutation. Help is read-only; confirmation does not grant mutation permission.
The model in one minute
ConfigHub treats configuration as data: fully materialized YAML stored in a versioned database, not code or templates. Mutations go through server-side functions on that data. Delivery, policy, and audit all hang off that model.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed e1971c804ab0
- 12d ago First seen · 243 lines · 68 tokens per session scan A 997293601596
confighub-core is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 4,724 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…