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 agentmods add skills/netmindai-open/narranexus/officeclinpx skills add NetMindAI-Open/NarraNexus --skill officecligit clone --depth 1 https://github.com/NetMindAI-Open/NarraNexusWhat 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 | $0.00056 | $0.07727 |
| Opus 5 | $0.00028 | $0.03864 |
| Sonnet 5 | $0.00011 | $0.01545 |
| Haiku 4.5 | $0.00006 | $0.00773 |
Grade C, and why
officecli scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
NOT try to install, download, or `curl | bash` it. Just call it directly. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
NOT try to install, download, or `curl | bash` it. Just call it directly. How it starts
The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
officecli
AI-friendly CLI for .docx, .xlsx, .pptx. Single binary, no dependencies, no Office installation needed.
Availability
officecli is pre-installed on this platform and already on your PATH — do
NOT try to install, download, or curl | bash it. Just call it directly.
Sanity-check once with officecli --version. In the rare case it is missing
(command not found), do NOT attempt a global install (it will be blocked in the
cloud sandbox and is unnecessary locally). Instead call
send_message_to_user_directly and tell the user that officecli is unavailable in
this environment so they can report it — then fall back to another approach.
Strategy
L1 (read) → L2 (DOM edit) → L3 (raw XML). Always prefer higher layers. Add --json for structured output.
Before doc work, check Specialized Skills (bottom of this file). Fundraising decks, academic papers, financial models, dashboards, and Morph animations need their own skill loaded first — load_skill once, then proceed.
Live preview in the panel (NarraNexus — IMPORTANT)
The user CANNOT open a raw .pptx / .docx / .xlsx in this chat. Whenever you
create or edit a document, open a LIVE preview in the right-side panel so the
user watches it take shape as you build it. Treat this as the delivery step — a
document the user can't see is not delivered.
Register FIRST, then build. The live refresh only works while the preview
is open, so you MUST register the document as an artifact immediately after
officecli create — BEFORE you add any slides/content — and then keep editing.
The user then watches it build slide by slide. If you register only at the end,
the user stares at an empty panel the whole time and the point is lost.
Name the file meaningfully, and make the title match the filename. The panel
tab shows the artifact title; if that differs from the workspace filename, the
user can't find the file they're looking at. So give the document a real,
descriptive filename up front (e.g. q4-report.pptx, not a generic deck.pptx)
and pass that same filename as the title. Keep filenames simple —
lowercase, hyphens/underscores, no spaces or special characters (spaces also
make the officecli path string harder to keep identical).
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.
- 2d ago First seen · 481 lines · 56 tokens per session scan C 938c3486feef
officecli is a skill published in the GitHub repository NetMindAI-Open/NarraNexus (84 stars, last pushed 9d ago), licensed Apache-2.0. It adds 56 tokens to every session and 7,727 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.