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 cub-mutategit 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/cub-mutate)<a href="https://agentmods.dev/skills/confighub/confighub-skills/cub-mutate"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/cub-mutate/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/cub-mutate"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/cub-mutate.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 | $0.00080 | $0.05202 |
| Opus 5 | $0.00040 | $0.02601 |
| Sonnet 5 | $0.00016 | $0.01040 |
| Haiku 4.5 | $0.00008 | $0.00520 |
Grade A, and why
cub-mutate 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cub-mutate
Execution mode: follow references/execution-modes.md. This Skill grants no automatic tool permission. After an exact diff and scope preview, standalone use submits one requested Unit mutation to the host permission system; an external overlay may stop it before Bash.
The get / modify / write-back loop for ConfigHub Units.
The rule
Prefer a function over a hand-edit. Functions like set-container-image, set-replicas, set-env-var, the defaults family — hermetic, idempotent, comment-preserving, and produce clean revisions. Hand-editing YAML is the fallback when no function fits.
And write the invocation so it works somewhere else too. A mutation is rarely a one-off: it runs across whatever selection you give it, it propagates to every downstream variant, and — because an upgrade now replays the upstream's recorded invocations against each variant rather than copying the paths they touched — it will be re-run later against data that has changed since. See Write invocations that generalize.
When to use
- Any single-field change: image, replicas, env var, port, annotation, label, resource requests/limits, probe, security context, hostname.
- Applying the defaults functions to one or many Units.
- Bulk changes across multiple Units via
--where/--where-data— usually inside a ChangeSet (see below). - Making a change hold against the next promotion (
--protect), or working out why an earlier change missed some variants. - Restoring a Unit to a prior revision (or a ChangeSet's pre-open state).
- Patching metadata (labels, annotations) on one or many Units.
Do not load for
- Creating a new Unit (
confighub-core). - Pure inspection / query (
cub-query). - Setting up Triggers or ValidationErrors (
triggers-and-applygates).
Preflight gates
cub auth statussucceeds — it contacts the server's/meendpoint to confirm the token is still valid (not just local login state). If it fails, ask the user to runcub auth login(an interactive browser sign-in an agent cannot complete).- User has write permission on the target Space(s).
- The Space is covered by a
TriggerFilterID(or its Triggers are otherwise in place) so validation will enforce the change. If not, suggesttriggers-and-applygates— but don't block.
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 aed33304a4d3
- 9d ago Changed b97bfff1c3e0
- 12d ago First seen · 373 lines · 80 tokens per session scan A c8cb6115990f
cub-mutate is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 5,202 once invoked, about $0.0004 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…