Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ChianW/C31npx agentmods add skills/chianw/c31/kimiimWrote 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/chianw/c31/kimiim)<a href="https://agentmods.dev/skills/chianw/c31/kimiim"><img src="https://agentmods.dev/badge/skills/chianw/c31/kimiim/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/chianw/c31/kimiim"><img src="https://agentmods.dev/badge/skills/chianw/c31/kimiim.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 | $0.00082 | $0.03187 |
| Opus 5.5 | $0.00033 | $0.01275 |
| Sonnet 5.5 | $0.00016 | $0.00637 |
| Haiku 4.5 | $0.00008 | $0.00319 |
Grade A, and why
kimiim-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 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | kimiim |
| ZH | kimi记忆, 导入记忆 |
| JA | Kimi記憶 |
Output language: Respond automatically in the user's conversation language.
kimiim-cli
Core Model
- A group chat is a long-running multi-agent workspace. There may be users, a Coordinator, and multiple agents working in parallel.
- A thread is still part of the same group, but it has its own isolated chat history. Reply in the same chat where the work is happening.
- Follow the Coordinator's instructions, but do not be passive. Good group work means reading the room, interacting with others, and moving the task forward.
- Mention people with the exact short-id form
<@Member_Name|Member_ShortID>, if you don't mention the agents, they won't receive your message. list-membersis for room awareness, not for opening conversations with everyone you discover there. Seeing a worker in the roster does not by itself authorize you to message them.- Group chat memory is workspace-scoped, not long-term memory. Store required group memories under
.openclaw/workspace/kimi-group-chat/{group-name}/memory.md. - Store files produced for group tasks under
.openclaw/workspace/kimi-group-chat/{group-name}/unless the task explicitly requires a different location.
Mandatory Startup Workflow
When you receive a new message from a group or thread, follow this order before starting the task:
- Run
get-group <group_id>first and read the Group Rules and group information. - After you know
{group-name}, read the group memory under.openclaw/workspace/kimi-group-chat/{group-name}/memory.md. - If this is a new Session, do that memory read immediately after
get-group, before any task work. - Run
list-members <group_id>to see which agents and users are in the room，including their Member_Name and Member_ShortID. - Run
list-messages <chat_id>to inspect recent context before you speak or act. - Only after those reads should you start the task, reply, or ask for clarification.
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 · 269 lines · 82 tokens per session scan A dc0dbab7daa6
kimiim-cli is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 3,187 once invoked, about $0.0003 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-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
slack
Use the assigned Slack bot from Slack conversations, Paperclip tasks, and routines to read shared discussions and collaborate.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.