Development instructions for KimiHarness, a Tauri desktop application with a Vite frontend and Rust backend.

Use them to run the app, build it, check TypeScript, probe the live daemon, and test the interface in a browser with Playwright.

They document the required development and build process, the daemon communication checks, and known pitfalls that can cause stale processes, failed builds, or incorrect protocol assumptions.

harness-dev — Skill for Claude Code and Codex by LokarBOA/kimiscope

Install

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.

Any agent

npx skills add LokarBOA/kimiscope --skill harness-dev

Clone the repo

git clone --depth 1 https://github.com/LokarBOA/kimiscope

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lokarboa/kimiscope/harness-dev/github.svg)](https://agentmods.dev/skills/lokarboa/kimiscope/harness-dev)

Your own site

<a href="https://agentmods.dev/skills/lokarboa/kimiscope/harness-dev"><img src="https://agentmods.dev/badge/skills/lokarboa/kimiscope/harness-dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lokarboa/kimiscope/harness-dev"><img src="https://agentmods.dev/badge/skills/lokarboa/kimiscope/harness-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 496 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00047	$0.00496
Opus 5.5	$0.00019	$0.00198
Sonnet 5.5	$0.00009	$0.00099
Haiku 4.5	$0.00005	$0.00050

Measured 2mo ago against content hash 94b1d4df7659, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-dev scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- The daemon must be running (`curl http://127.0.0.1:58627/api/v1/healthz`); the app auto-starts it, probes do not.

.kimi-code/skills/harness-dev/SKILL.md · 36 lines

What it actually says

KimiHarness dev loop

Read AGENTS.md first — it has the architecture and the daemon protocol facts. Do not re-derive them by probing.

Run in dev

Two processes (do NOT use npm run tauri dev under a background task manager — it gets killed and orphans children):

npm run dev (vite, port 5173)
cd src-tauri && cargo run --no-default-features (opens the window; debug builds load devUrl)

HMR applies to frontend changes. Rust changes need a cargo restart.

Build

npm run tauri build → exe + installers under src-tauri/target/release/bundle/. Kill any running release app.exe first (Windows locks it; the build fails with "Access is denied").

Verify

npx tsc -b must be clean before anything is called done.
Protocol changes: verify against the live daemon with a probe script (scripts/probe-*.mjs pattern, see the live-probe skill). Never code against assumed frame shapes.
UI behavior: run the frontend in a plain browser and drive it with Playwright — npm run dev:token (writes the gitignored public/dev-token.json), npm run dev, open http://localhost:5173. getConnectionInfo falls back to the token file automatically when Tauri IPC is absent.
UI state: zustand v5 — no ?? [] / ?? {} inside selectors (infinite render loop; see AGENTS.md).
The daemon must be running (curl http://127.0.0.1:58627/api/v1/healthz); the app auto-starts it, probes do not.

Conventions

Rust stays thin (daemon lifecycle + token only). All API I/O is frontend fetch/WebSocket.
Keep dependencies as-is (no new UI frameworks); Tailwind v4 for styles, dark theme.
Probe scripts go in scripts/, captures in reference/, and are throwaway — archive probe sessions after.

Changes

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.

2mo ago First seen · 36 lines · 47 tokens per session scan A 94b1d4df7659

Subscribe to this mod's changes

harness-dev is a skill published in the GitHub repository LokarBOA/kimiscope (2 stars, last pushed 13d ago), licensed MIT. It adds 47 tokens to every session and 496 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

harness-dev next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-devLokarBOA/kimiscope	Skill	2	13d ago	MIT	A	47	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

harness-dev