Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.
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 enricoros/big-AGI --skill tape-opensgit clone --depth 1 https://github.com/enricoros/big-AGIWrote 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/enricoros/big-agi/tape-opens)<a href="https://agentmods.dev/skills/enricoros/big-agi/tape-opens"><img src="https://agentmods.dev/badge/skills/enricoros/big-agi/tape-opens/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/enricoros/big-agi/tape-opens"><img src="https://agentmods.dev/badge/skills/enricoros/big-agi/tape-opens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.01117 |
| Opus 5 | $0.00030 | $0.00558 |
| Sonnet 5 | $0.00012 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
tape-opens 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tape-opens - stack-unwind review
You are a fresh instance with NO access to the conversation you are about to review. That is by design: you must not assume anything about the user, the project, or what a "normal" conversation looks like.
The concept: long working sessions are depth-first. The user starts with an objective, drills into one aspect (leaving opens behind), drills deeper inside that, and so on - a stack, not a list. Your job is to reconstruct the whole thread as a stack-unwind tree: the main tasks that actually got done, checked and struck through, and everything raised-but-never-resolved as unchecked opens, nested at the stack depth where each was abandoned.
Step 1 - census (deterministic, run exactly this)
bash ${CLAUDE_SKILL_DIR}/census.sh ${CLAUDE_SESSION_ID} $ARGUMENTS
It prints SESSION, USER_PROMPTS, SPAN, BUDGET, SPINE (a file path), SPINE_BYTES. If it prints ERROR, stop and report that error text as your final message.
BUDGET is the sizing law and it is not yours to adjust, in either direction. Why it exists: opens are created by descents, and descents happen at user prompts - not at tokens, which are dominated by tool noise. So the tree size is computed from the measured prompt count (round(1.5 * sqrt(USER_PROMPTS)), clamped 5..30) by the script, before any model is involved. A zero-knowledge instance like you would otherwise default to "about a page" no matter the thread; the computed budget is what makes a 15-prompt evening yield 6 nodes and a 5-day monster yield 25, consistently, on every run.
Step 2 - read the spine
Read the SPINE file completely (use offset/limit chunks if it is large). It is the conversation reduced to plain chronological text:
[USER <timestamp>]- a user prompt (truncated to 800 chars)[AI]- an assistant text reply (truncated to 400 chars)[INTERRUPTED]- the user cut the assistant off mid-turn; a frame likely got popped without unwinding - strong open signal nearby[TASK-RESULT]- a background subagent returned; its findings may contain deferred items[COMPACTED SUMMARY <date>]- condensed earlier history; treat its contents as thread events[USER dead-branch <timestamp>]/[AI dead-branch]- content from an abandoned or rewound timeline: the user backtracked and the thread continued differently. Real work and real opens can live there, but the live thread wins on any conflict, and nothing from a dead branch counts as done unless the live thread confirms it
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.
- 11d ago First seen · 61 lines · 60 tokens per session scan A d320b59ba178
tape-opens is a skill published in the GitHub repository enricoros/big-AGI (7,119 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,117 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 2026-08-30.
Other skills, from other repositories
creating-slides
Slide/PPT creation skill that provides complete slide creation, editing, and management capabilities. Use when users need to create slides, make presentations, edit slide content, or manage slide projects. CRITICAL - When user message contains [@slideproject:...] mention, you MUST load this skill first before any…
micro-app-architect
Use FIRST for Super Magic HTML micro-app work. Trigger even when the user does not say "micro-app", "HTML", or "window.Magic": when they ask to make/build/generate a usable interactive product such as an app, mini app, web page/site with controls, tool, form, calculator, generator, kanban…
self-media-composer
Use when the user wants to create, extend, or edit self-media posts or card/article projects for Rednote/Xiaohongshu, Instagram, WeChat Official Accounts, or similar platforms. Trigger on [@selfmediaproject:...], create/add post, make cards, generate social cards, write WeChat article, multilingual self-media…
canvas-designer
Core canvas design skill covering project management, multimedia principles, AI image generation, web image search, and design marker processing. Load for any canvas design task. CRITICAL - When user message contains [@designcanvasproject:...] or [@designmarker:...] mentions, or when the user wants to generate…
develop-data-analysis-dashboard
Data analysis dashboard (instrument panel) development skill. Use when users need to develop data dashboards, create/edit Dashboard projects, build large-screen data boards, or perform dashboard data cleaning. Includes dashboard project creation, card plan, data cleaning (datacleaning.py), card management tools…
antd-style-to-tailwind
Migrate existing antd-style CSS-in-JS (createStyles) components to Tailwind CSS utility classes with full dark mode support, following the project's style system transition strategy. Use when the user asks to migrate, convert, or rewrite antd-style components to Tailwind, or when working on new components in files…