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-add-new-source/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-add-new-source)<a href="https://agentmods.dev/skills/kkeril/colombo/colombo-add-new-source"><img src="https://agentmods.dev/badge/skills/kkeril/colombo/colombo-add-new-source/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-add-new-source"><img src="https://agentmods.dev/badge/skills/kkeril/colombo/colombo-add-new-source.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 | $0.00061 | $0.03004 |
| Opus 5 | $0.00030 | $0.01502 |
| Sonnet 5 | $0.00012 | $0.00601 |
| Haiku 4.5 | $0.00006 | $0.00300 |
Grade A, and why
colombo-add-new-source 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 9d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Colombo add new source skill
This skill adds one real connected system to Colombo. The user may say "source," but MCP is the tool/access layer; the source of truth is the actual system: repo, metrics, logs, payments, analytics, database, docs, deploy system, or support tool.
Care means Colombo does the boring setup work itself, explains only when the owner needs to decide or act, and turns source setup into one clear next action at a time.
Onboarding must call this skill for all source work. Keep MCP discovery, setup preparation, sampling, source-use recommendations, approvals, demo answers, and generated test messages here instead of in $colombo-onboarding.
Source setup principles
- Ask one question at a time.
- If the next source is not already chosen, ask what source the owner wants next; when product or repo evidence exists, recommend the best next source first and say why.
- If the owner names exactly one source, accept that source and make it useful before suggesting anything else. Do not turn a single-source request into source shopping.
- If the owner already names multiple sources, do not make them repeat the list. Turn it into one combined source plan, choose the order, and explain the order briefly.
- GitHub/GitLab code access is the preferred first source when the owner allows it because code reveals integrations, services, jobs, SDKs, and operational systems.
- Prefer read-only GitHub/GitLab MCP access for private repositories; do not make manual repository transfer the default.
- Do the work before asking: inspect local files/configs, use existing MCP access, install or prepare the relevant MCP connector when available, and write exact config/env placeholders.
- Explain only what matters to the owner: why this source helps, what they need to fill locally, what sample was checked, and what Colombo will use the source for.
- Use only read-only MCP tools, local repo reads, and narrow metadata/sample queries.
- Ask the owner to put private auth values in the exact local config/env file and reply
done; do not ask for values in chat. - Batch missing local placeholders into one owner action when they belong in the same file. If a connector needs a separate UI step, ask that as the next single action.
- Discover exposed MCP tool names and write only owner-approved read-only tools into
codex_mcp_enabled_tools. - MCP server access must also be read-only at the provider level; the Codex sandbox does not make external systems read-only.
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.
- 9d ago First seen · 158 lines · 0 tokens per session scan A ae45ef7c3a90
colombo-add-new-source is a skill published in the GitHub repository kkeril/colombo (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 3,004 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…
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…