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 agentmods add skills/getkimchi/kimchi/improvenpx skills add getkimchi/kimchi --skill improvegit 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/improve)<a href="https://agentmods.dev/skills/getkimchi/kimchi/improve"><img src="https://agentmods.dev/badge/skills/getkimchi/kimchi/improve.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00445 |
| Opus 5 | $0.00008 | $0.00222 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
improve 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 5d 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.
What it actually says
Skill Curator (/improve)
Use this skill when the user asks to run the self-improvement loop or consolidate skills.
What the curator does
The curator consolidates agent-created skills — skills you created during sessions via skill_manage action=create. It does NOT touch bundled or harness skills. It does NOT delete anything — it archives (recoverable from .archive/).
Step 1: Check curator status
Call curator action=status to check if a background run is in progress.
If the response shows "running": true with a recent last_run_at (< 4h ago), report:
"The curator is currently running in the background. Check back later or wait for it to finish."
Then stop.
Step 2: Confirm with user
Before running, confirm:
"I'll review your agent-created skills and consolidate overlapping ones into umbrellas. No skills will be deleted — only archived (recoverable). Want to proceed? (Add 'dry-run' to preview without changes.)"
If the user says dry-run: call skill_manage action=list to show agent-created skills, describe what you'd consolidate, then stop without calling curator action=run.
Step 3: Run the curator
Call curator action=run.
The curator will:
- Apply auto-transitions (stale/reactivate/archive by age)
- Spawn a consolidation subagent with access to skill_manage, skill_view, skill_list
- Return a structured summary
Step 4: Report results
Present the summary from the curator tool result:
- How many skills were consolidated (X → umbrella)
- How many were archived
- If nothing changed: "No consolidations found. Your skill library is already well-organized."
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.
- 5d ago First seen · 52 lines · 16 tokens per session scan A 4019bb6f606c
improve is a skill published in the GitHub repository getkimchi/kimchi (2,218 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 445 once invoked, about $0.0001 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
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
testing-skill
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
slack-drafts
Create Slack message drafts in the user's own composer, as the user, through their per-user Slack OAuth. Drafting only — the user reviews and sends from Slack.