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/gpt-cmdr/ras-commander/dev_invoke_kimi-clinpx skills add gpt-cmdr/ras-commander --skill dev_invoke_kimi-cligit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWhat 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 | $0.00190 | $0.03218 |
| Opus 5 | $0.00095 | $0.01609 |
| Sonnet 5 | $0.00038 | $0.00644 |
| Haiku 4.5 | $0.00019 | $0.00322 |
Grade A, and why
dev_invoke_kimi-cli 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 2d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoking Kimi CLI (via Opencode)
Legacy Claude-only orchestration skill. This is not part of the standard production harness policy. It is excluded from the shared multi-harness corpus and should be used only when the user explicitly requests Kimi or Opencode/Kimi.
When the user explicitly requests Kimi or Opencode/Kimi, delegate the requested testing, quality assurance, or code review task to Opencode CLI using the Kimi K2.5 model. Write task instructions to TASK.md, invoke Opencode with Kimi K2.5, then read OUTPUT.md for results.
Pattern: Markdown File Handoff
Claude Code Opencode CLI + Kimi K2.5
| |
+-- Write TASK.md ------------------+
| (test/review requirements) |
| |
+-- Execute: opencode run -m |
| opencode/kimi-k2.5-free |
| "Read TASK.md..." |
| |
| +-- Reads TASK.md
| +-- Generates tests/review
| +-- Writes OUTPUT.md
| |
+-- Read OUTPUT.md <----------------+
| (tests + findings + results) |
v v
Benefits:
- Eliminates shell escaping issues
- Keeps context structured in reviewable files
- Enforces explicit output structure
- Supports both Opencode and Together.ai providers
- Excels at edge case detection
Legacy Model Selection
Codex is the production-supported second harness for this repository. Use this legacy Kimi path only when the user explicitly asks for Kimi or Opencode/Kimi.
Available Models
| Model | Provider | Use Case | Status |
|---|---|---|---|
opencode/kimi-k2.5-free |
Opencode (Moonshot) | Legacy explicit-request path; free tier | Verified |
opencode/kimi-k2.5 |
Opencode (Moonshot) | Paid tier with higher rate limits | Available |
togetherai/moonshotai/Kimi-K2.5 |
Together.ai | Alternative provider | Verified |
togetherai/moonshotai/Kimi-K2-5 |
Together.ai | Alternative naming convention | Available |
What ships with it
1 file 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.
- 2d ago First seen · 443 lines · 190 tokens per session scan A 6a400945b5a7
dev_invoke_kimi-cli is a skill published in the GitHub repository gpt-cmdr/ras-commander (78 stars, last pushed 2d ago), licensed MIT. It adds 190 tokens to every session and 3,218 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…