getkimchi/kimchi is a terminal-based coding agent that helps with software development through Kimchi’s language-model infrastructure. It can run tasks with one selected model or coordinate multiple models, with model roles chosen by its orchestration system.
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 getkimchi/kimchi --skill pptxgit clone --depth 1 https://github.com/getkimchi/kimchiWrote 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/getkimchi/kimchi/pptx)<a href="https://agentmods.dev/skills/getkimchi/kimchi/pptx"><img src="https://agentmods.dev/badge/skills/getkimchi/kimchi/pptx/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/getkimchi/kimchi/pptx"><img src="https://agentmods.dev/badge/skills/getkimchi/kimchi/pptx.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 | $0.00038 | $0.02427 |
| Opus 5.5 | $0.00015 | $0.00971 |
| Sonnet 5.5 | $0.00008 | $0.00485 |
| Haiku 4.5 | $0.00004 | $0.00243 |
Grade A, and why
pptx 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 yesterday.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pptx
All commands run the bundled runtime. Replace <deck> with the user's path.
- Get this skill's directory from the
skill_viewresult (Skill directory:line) — call it<skill-dir>. Always use that value; never search the filesystem for the script. - With the kimchi binary:
BUN_BE_BUN=1 kimchi <skill-dir>/scripts/pptx.mjs <command> ... - On Windows/Git Bash the same
BUN_BE_BUN=1 kimchi ...prefix works. - Fallback if
kimchiis not on PATH and Node is:node <skill-dir>/scripts/pptx.mjs ...
read <deck> [start-end]
Slides as Markdown with locators — [shape "…"] names, [table N] indices — the exact
names edit needs. Speaker notes print under Notes:.
- 20 slides per call. For longer decks, read ranges:
read deck.pptx 1-20, then21-40, etc. The output tells you the next range to request. - Summarize numbers, never retype them. Quote a number only when you'd burn it into the deck again; otherwise reference it ("Q3 ARR row") to keep summaries accurate.
inspect <deck>
Name every slide layout, its placeholders (type, idx), and slide dimensions; list every
shape by exact name. Run this before edit — edit ops take the names printed here,
unchanged. No inspect → no edit.
check <deck>
Static review. Exit code 1 when anything is flagged — treat flags as
heuristics, named plainly ("likely text overflow"). Run after every edit
pass; if check reports findable defects, review a flagged area before
finishing. Heuristics can false-positive on tight text — read the exact slide
before rewriting.
text-overflow— text estimated past its shape box.overlap— two text shapes whose boxes intersect (spilled text colliding with the shape below it).low-contrast— dark text on a dark slide background (explicit or inherited).off-slide— shapes past the slide edge.missing-alt-text— pictures without alt text.monotony— deck-level: most slides are title-and-text only. Vary layouts (seedeck-design.md).dead-space— a slide whose content occupies under half of its area.
What ships with it
2 files 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.
- yesterday First seen · 172 lines · 38 tokens per session scan A dac25ce4707b
pptx is a skill published in the GitHub repository getkimchi/kimchi (2,276 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 2,427 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 2026-10-24.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.