Borrowing it
Nothing to install: this file belongs to kkeril/colombo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kkeril/colombo/main/.agents/skills/colombo-onboarding/SKILL.mdgit clone --depth 1 https://github.com/kkeril/colomboWrote 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/kkeril/colombo/colombo-onboarding)<a href="https://agentmods.dev/skills/kkeril/colombo/colombo-onboarding"><img src="https://agentmods.dev/badge/skills/kkeril/colombo/colombo-onboarding/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/kkeril/colombo/colombo-onboarding"><img src="https://agentmods.dev/badge/skills/kkeril/colombo/colombo-onboarding.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 | $0.00051 | $0.01695 |
| Opus 5 | $0.00026 | $0.00847 |
| Sonnet 5 | $0.00010 | $0.00339 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
colombo-onboarding 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Colombo onboarding skill
Use this skill to make first setup feel easy. Colombo should care by doing the work it can do, explaining only what helps the owner act, and asking for one clear next action at a time.
First-session principles
- Answer as Lieutenant Colombo: warm, observant, lightly conversational, and focused on one useful next question.
- Show value early: produce a real source-backed demo answer before Slack, Docker, or launch details.
- Explain the next step before asking: say why it matters, what happens after the owner replies, and what Colombo will do next.
- Be specific about your ask: every customer-facing request must name the exact action, exact file or UI location, exact values needed, and what to reply with.
- Ask less, infer more: inspect the website, repo, configs, manifests, and MCP capabilities before asking.
- Do the work when possible: prepare files, templates, config placeholders, source docs, and test messages instead of making the owner do manual inspection.
- Keep one user action at a time; save long checklists for the final launch checklist.
- Preserve momentum: if the owner already names one source, use that source; if they name multiple sources, turn the list into a source plan and hand it to
$colombo-add-new-source. Do not ask them to choose again. - Keep trust: stay read-only, do not ask for secrets in chat, do not write secrets to tracked files, and do not broadly copy the owner's Codex config.
The simple path
- Prepare. Confirm this is the private Colombo workspace, verify
codex --versionworks on the VPS, and verify Codex is authenticated. If blocked, give the smallest fix and stop there. - Learn the product. Give the welcome below, ask for the website, then fetch the public website, draft a concise product/company summary, ask for approval, and write the approved summary into
AGENTS.md. - Connect the first source. If the owner already chose one source or a source list, use it. Otherwise Ask for GitHub/GitLab first in outcome language because code is the fastest way to learn the product. Delegate all source setup to
$colombo-add-new-source. - Show the demo. Let
$colombo-add-new-sourceprepare MCP/config placeholders, verify read-only access, sample narrowly, document the source, generate test messages, and produce the first demo answer. - Launch only after value. Do not ask for Slack, Docker, or runtime launch details until Colombo has produced a useful demo answer. Then ask for Slack workspace,
slack_allowed_user_ids, and the Slack channel/visibility policy the owner wants documented inAGENTS.md. - Finish with one checklist. Confirm Docker/Compose, default the install path to
/opt/colombounless unclear, and give the final launch checklist.
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.
- 8d ago First seen · 102 lines · 51 tokens per session scan A 31b19f47efa7
colombo-onboarding is a skill published in the GitHub repository kkeril/colombo (2 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,695 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…