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 Bumblebiber/its-over-9k --skill companion-bundlesgit clone --depth 1 https://github.com/Bumblebiber/its-over-9kWrote 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/bumblebiber/its-over-9k/companion-bundles)<a href="https://agentmods.dev/skills/bumblebiber/its-over-9k/companion-bundles"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/companion-bundles/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/bumblebiber/its-over-9k/companion-bundles"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/companion-bundles.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 | $0.00095 | $0.01075 |
| Opus 5 | $0.00048 | $0.00537 |
| Sonnet 5 | $0.00019 | $0.00215 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
companion-bundles 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 10d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
companion-bundles — one-command companion install
First install or unknown delta:
/o9k-init(o9k-core) — mandatory interview (detection, bundle choice, conflict migration, git). Known bundle name (minimal/recommended/max) → this skill directly.
o9k's pillars are Claude Code plugins. The companions (memory backend, live
docs, methodology, task graph, symbols) live in other ecosystems — npm, uvx,
MCP, other plugin marketplaces. This skill installs a curated, internally
conflict-free subset in one shot via install/o9k-companions.sh.
Each bundle is guaranteed conflict-free: no two tools in it claim the same o9k concern (see docs/COMBINING.md and using-o9k arbitration).
Bundles
| Bundle | Contents | For |
|---|---|---|
minimal |
hmem (memory) · Context7 (docs) · Ponytail (code minimalism) | Any project. Zero-conflict foundation, biggest payoff per install. |
recommended |
minimal + superpowers (methodology) + beads (task graph) + Serena (symbols) | The tested full stack. |
max |
recommended + ast-grep (structural) + ccusage (cost) | Large/polyglot repos wanting every conflict-free companion. |
How to run
- Dry-run first — mandatory. Prints the plan and prerequisite check;
executes nothing:
install/o9k-companions.sh recommended - Review the plan with the user, then execute the shell-installable steps:
install/o9k-companions.sh recommended --run - Install the plugin-based companions (superpowers, Ponytail) yourself —
claude plugin marketplace add <owner>/<repo>andclaude plugin install <name>are regular shell commands, not the/pluginREPL-only slash command. Then tell the user to run/reload-pluginsonce (that step genuinely can't run from a shell). Anything the printed plan flags as truly manual (e.g. beads has no npm/go/brew package to script against) stays with the user — point at the upstream repo, don't guess an install command.
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.
- 10d ago First seen · 83 lines · 95 tokens per session scan A 989938033311
companion-bundles is a skill published in the GitHub repository Bumblebiber/its-over-9k (0 stars, last pushed 13d ago), licensed MIT. It adds 95 tokens to every session and 1,075 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…