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/lokarboa/kimiscope/harness-devnpx skills add LokarBOA/kimiscope --skill harness-devgit clone --depth 1 https://github.com/LokarBOA/kimiscopeWrote 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/lokarboa/kimiscope/harness-dev)<a href="https://agentmods.dev/skills/lokarboa/kimiscope/harness-dev"><img src="https://agentmods.dev/badge/skills/lokarboa/kimiscope/harness-dev.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 | $0.00047 | $0.00496 |
| Opus 5 | $0.00023 | $0.00248 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
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 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.
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. 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 -bmust be clean before anything is called done.- Protocol changes: verify against the live daemon with a probe script (
scripts/probe-*.mjspattern, see thelive-probeskill). 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 gitignoredpublic/dev-token.json),npm run dev, open http://localhost:5173.getConnectionInfofalls 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 inreference/, and are throwaway — archive probe sessions after.
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 · 36 lines · 47 tokens per session scan A 94b1d4df7659
harness-dev is a skill published in the GitHub repository LokarBOA/kimiscope (2 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 496 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…