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 CraftOS-dev/CraftBot --skill agent-app-importergit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/agent-app-importer)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/agent-app-importer"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/agent-app-importer/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/craftos-dev/craftbot/agent-app-importer"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/agent-app-importer.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 | $0.00039 | $0.02210 |
| Opus 5.5 | $0.00016 | $0.00884 |
| Sonnet 5.5 | $0.00008 | $0.00442 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
agent-app-importer 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 23d 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.
Agent App Importer
Bring existing apps into this CraftBot: marketplace installs (pre-built apps from the catalogue), Agent App project imports from a ZIP, a local folder path, or a git URL, and conversions of foreign (non-Agent-App) apps — which are REBUILDS: the original code becomes reference material and the behavior is re-implemented on this platform. Be honest about that cost before converting: nothing of the original code runs here.
Which path?
| The user has… | Do this |
|---|---|
| An app name / "what's in the marketplace?" | agent_app_marketplace_list → match by name → agent_app_marketplace_install(app_id=...) |
A .zip, a project folder path, or a git URL of a Agent App |
agent_app_import(source=...) — one door for all three |
| A foreign (non-Agent-App) codebase | agent_app_convert(source=...) — a full REBUILD; tell the user first |
Conversion (foreign apps)
agent_app_convert(source=..., name?, description?) scaffolds a fresh Agent App
project, ships the original source read-only at reference/source/,
synthesizes requirements.md FROM that source, and dispatches the normal
supervised build to the project's session — you are done after this call;
progress streams to the project tab and the system announces the result.
Pass description when the user said what matters ("keep the board, skip
the admin panel"). If the source turns out to BE a Agent App project the
action errors and points you to agent_app_import.
Marketplace install
agent_app_marketplace_list— resolve the exactapp_id(never guess ids; match the user's words against names/descriptions).agent_app_marketplace_install(app_id="...", name="...")— downloads, registers, and launches the app in one step.- On success, tell the user the app name and URL. Marketplace apps are pre-built and pre-verified upstream — no walk-verify needed. NOTE: apps still in the legacy V1 format are rejected with a clear error — the platform only runs current-format Agent Apps. Tell the user that app hasn't been re-published for this version of CraftBot yet; do not improvise a workaround.
- On a launch error, treat it like any build failure: read ALL errors,
fix (the project is a normal Agent App project under the ownership rules),
agent_app_notify_readyagain.
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.
- 23d ago First seen · 158 lines · 39 tokens per session scan A b54946f49e73
agent-app-importer is a skill published in the GitHub repository CraftOS-dev/CraftBot (395 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,210 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
development-estimation
Use when estimating time, effort, cost, or complexity for features, projects, refactors, and bug backlogs. Produces defensible estimates via triage, decomposition, risk handling, and confidence intervals, with clear assumptions and validation steps.
product-roadmap
Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies, choosing between Now/Next/Later or quarterly formats, or presenting roadmap tradeoffs to stakeholders.
sales-call-prep
Prepare for a sales call with account context, attendee research, and suggested agenda. Works standalone with user input and web research, supercharged when you connect your CRM, email, chat, or transcripts. Trigger with "prep me for my call with [company]", "I'm meeting with [company] prep me", "call prep [company]"…
product-stakeholder-comms
Draft stakeholder updates tailored to audience — executives, engineering, customers, or cross-functional partners. Use when writing weekly status updates, monthly reports, launch announcements, risk communications, or decision documentation.
sales-daily-briefing
Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".
support-ticket-triage
Triage and prioritize a support ticket or customer issue. Categorize issues, assign priority (P1-P4), and recommend routing.