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 satasuk03/kimi-plugin-cc --skill kimi-k2-promptinggit clone --depth 1 https://github.com/satasuk03/kimi-plugin-ccWrote 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/satasuk03/kimi-plugin-cc/kimi-k2-prompting)<a href="https://agentmods.dev/skills/satasuk03/kimi-plugin-cc/kimi-k2-prompting"><img src="https://agentmods.dev/badge/skills/satasuk03/kimi-plugin-cc/kimi-k2-prompting/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/satasuk03/kimi-plugin-cc/kimi-k2-prompting"><img src="https://agentmods.dev/badge/skills/satasuk03/kimi-plugin-cc/kimi-k2-prompting.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00022 | $0.00368 |
| Opus 5.5 | $0.00009 | $0.00147 |
| Sonnet 5.5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
kimi-k2-prompting 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 1mo 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
Kimi K2.7 Prompting
Use this skill when tightening a delegated request into a strong prompt for Kimi K2.7 before calling task, reason, or review.
Kimi's coding model is strong at multi-step agentic coding and tool use, but it works best when the request is explicit and focused rather than open-ended.
Core rules:
- State the goal in one or two sentences before any supporting detail.
- Name the relevant files, directories, or modules instead of describing them vaguely.
- Call out constraints explicitly: languages or frameworks to use, things not to touch, style or testing requirements.
- Give clear acceptance criteria — what "done" looks like, including how it should be verified (tests, a command to run, a behavior to observe).
- Prefer one focused task per prompt. Split unrelated asks into separate
task/reasoncalls rather than bundling them. - For read-only work (
reason, investigation, review), say so explicitly so Kimi does not assume it should start editing. - For follow-up instructions on the same thread (
--resume-last), send only the delta instruction instead of restating the whole original prompt, unless the direction changed materially.
Prompt shape to aim for:
- Goal — what should exist or be true when this is done.
- Context — relevant files, directories, prior findings, or error messages.
- Constraints — anything Kimi must or must not do.
- Acceptance criteria — how to know the result is correct.
Keep the prompt compact. Extra scaffolding does not help K2.7 as much as a precise, unambiguous task statement.
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.
- 1mo ago First seen · 28 lines · 22 tokens per session scan A a3332f3addbb
kimi-k2-prompting is a skill published in the GitHub repository satasuk03/kimi-plugin-cc (2 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 368 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
agent-prompt-engineering
Use when building or revising the system prompt for a product agent and you need an eval-backed boundary, tool-use, grounding, and output contract. Not for board-specialist adapters or lane capability projections, which follow model-lanes generators and controller policy.
refine
Crossover layer between the user's intent and LLM execution: takes a raw prompt (terse, frustrated, ambiguous, or shorthand), resolves every vague reference to a concrete artifact, recalls past decisions and lessons, and compiles a verifiable execution contract BEFORE any code is touched. Invoke explicitly as $refine…
llm-eng-checks
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with omp-native tools (bash for real API round-trips, read/grep for the repo's own client, no vendor-plugin dependency, provider-agnostic). PRIME RULE — no LLM feature is…
cursor-prompting
Internal guidance for composing compact, operator-style prompts for cursor-agent across coding, review, diagnosis, and research tasks.
optimize
Rephrase a rough prompt to follow prompt-engineering best practices WITHOUT changing its meaning, then show it for review without executing. Use when the user runs /petprompt:optimize or asks to rewrite/clean up/optimize their prompt before running it.
codex-prompting
Internal guidance the stereo:codex-rescue subagent uses to compose prompts for Codex CLI models (coding, review, diagnosis, research); the main session does not load it.