Kilo Code is an open-source AI coding agent that works inside VS Code and JetBrains, from the command line, or through cloud services. Developers use it to build software with AI models, switch between providers, and run cloud agents or automated code reviews. The catalogue includes eleven skills, eight agents, and one instruction for Kilo Code.
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 Kilo-Org/kilocode --skill kilocode-merge-minimizergit clone --depth 1 https://github.com/Kilo-Org/kilocodeWrote 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/kilo-org/kilocode/kilocode-merge-minimizer)<a href="https://agentmods.dev/skills/kilo-org/kilocode/kilocode-merge-minimizer"><img src="https://agentmods.dev/badge/skills/kilo-org/kilocode/kilocode-merge-minimizer/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/kilo-org/kilocode/kilocode-merge-minimizer"><img src="https://agentmods.dev/badge/skills/kilo-org/kilocode/kilocode-merge-minimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00076 | $0.01348 |
| Opus 5 | $0.00038 | $0.00674 |
| Sonnet 5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
kilocode-merge-minimizer 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 13d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kilo Merge Minimizer
Use this skill whenever a normal development task touches shared upstream-owned code and includes Kilo-specific behavior, especially for marker cleanup, extraction work, or kilocode_change annotations.
Do not use this skill when all changes are confined to Kilo-owned paths, including packages/kilo-vscode/, packages/kilo-ui/, and paths with kilocode in their name. Those files are not merged from upstream and do not need merge-minimization guidance. If a task also touches shared upstream-owned code, use this skill for the shared portion only.
Do not use this as the primary guide for upstream merge resolution. Upstream merges have their own instructions and should not duplicate that workflow here.
Goal
Minimize Kilo's long-term diff against upstream OpenCode while preserving behavior.
Prefer this shape for Kilo-specific additions:
- Shared upstream file contains only a minimal hook, import, call, registration, or config entry.
- Kilo-specific behavior lives in Kilo-owned code.
- Unavoidable shared-file changes have narrow
kilocode_changemarkers. - The annotation checker passes.
For changes to existing upstream behavior, prefer the smallest in-place shared-file diff with narrow markers. Do not move changed upstream logic into Kilo-owned code just to avoid textual conflicts, because that can create harder semantic merge conflicts.
Core Rules
- Use
script/check-opencode-annotations.tsas the source of truth for current shared scopes and exempt paths. - Use
script/upstream/fix-kilocode-markers.tsfor stale or broad markers, inspecting--dry-runoutput before applying changes. - Treat upstream-owned files as shared unless the checker or repo ownership rules exempt them.
- Put Kilo-owned UI, CLI, runtime logic, and tests in Kilo-owned paths where practical.
- Avoid adding Kilo business logic directly to shared files.
- Keep shared-file edits as close as possible to upstream shape.
- Do not change shared files unless the change is required for Kilo functionality, fixes a Kilo bug, or is a minimal targeted upstream-quality fix.
- Do not create a large Kilo-only fork for a general upstream-quality improvement. Prefer a minimal targeted fix, or leave the broader change for upstream.
- Do not duplicate upstream logic unless there is a concrete reason. If duplication is unavoidable, isolate the Kilo delta and keep the upstream dependency obvious.
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.
- 13d ago First seen · 122 lines · 76 tokens per session scan A cd218d1baa14
kilocode-merge-minimizer is a skill published in the GitHub repository Kilo-Org/kilocode (27,269 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,348 once invoked, about $0.0004 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
launch
You are a release engineer. Execute each phase in order. Each must fully complete before advancing. Do NOT ask for permission. Stop only if something is truly unfixable.
pair-loop
Coder reviewer handoff loop (claude/codex/cursor, roles swappable) with self-instrumented per-round cost tracking. Loops locally via HANDOFF.md until approved, then opens a PR with the full transcript.
commit
Quality gate runs FIRST. Do NOT commit if any gate fails.
gate
MANDATORY before every commit and push. All gates must pass — Gates 1–3 always run; Gates 4 (Docker) and 5 (Cloud) run only when applicable. Do NOT proceed if any gate fails — fix the issue first.
push
Quality gate re-runs before pushing. Do NOT push if any gate fails.
pr
Create a GitHub Pull Request with full AI review. Human approves and merges.