kimi-consultant

kimi-consultant is an agent for Claude Code from rube-de/cc-skills. It costs 384 tokens per session (3,045 once invoked), scanned C, original, MIT.

A review assistant that sends code, pull requests, algorithms, or solution ideas to Moonshot AI's Kimi K3 model for an outside analysis.

In plain words
What is it for?
Use it for code and pull-request reviews, algorithm analysis, long-context code reasoning, and creative problem-solving.
Why use it?
It provides another viewpoint when checking code or choosing between technical approaches.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the TodoWrite tool.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/My.

Part of the council plugin — 3 skills, 7 agents shipped together

Good fit Use it for code and pull-request reviews, algorithm analysis, long-context code reasoning, and creative problem-solving.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add rube-de/cc-skills
Claude Code
/plugin install council

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 3 skills, 7 agents.

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.

agentmods badge for kimi-consultant

README.md
[![agentmods](https://agentmods.dev/badge/agents/rube-de/cc-skills/kimi-consultant/github.svg)](https://agentmods.dev/agents/rube-de/cc-skills/kimi-consultant)
Your own site
<a href="https://agentmods.dev/agents/rube-de/cc-skills/kimi-consultant"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/kimi-consultant/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.

agentmods 80×15 button for kimi-consultant

Your own site · 80×15
<a href="https://agentmods.dev/agents/rube-de/cc-skills/kimi-consultant"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/kimi-consultant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 384 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00384 $0.03045
Opus 5 $0.00192 $0.01522
Sonnet 5 $0.00077 $0.00609
Haiku 4.5 $0.00038 $0.00304

Measured 10d ago against content hash b746bc048165, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

kimi-consultant scanned grade C 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

trap 'rm -rf "$sandbox"' EXIT # remove the sandbox even on error/interrupt
plugins/council/agents/kimi-consultant.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior technical consultant who leverages Moonshot AI's Kimi K3 model via the omp CLI for code review, PR review, algorithm analysis, and creative problem-solving. Kimi K3 offers strong coding capabilities, long-context reasoning, and unique perspectives on implementation approaches.

omp CLI Usage

The omp CLI (omp) provides access to Kimi K3 through the kimi-code provider, model k3 — the full invocation is omp -p --no-tools --model kimi-code/k3. Key patterns:

  • -p runs non-interactively (print result and exit).
  • --model kimi-code/k3 selects the model.
  • --no-tools disables omp's built-in read/bash/edit/write tools, so the model cannot inspect or modify the workspace through them. It does not make the session report-only on its own: --no-tools does not disable custom-tool discovery. omp still scans its working directory's .omp/tools/ and .claude/tools/ and import()s those modules at startup, executing their code regardless of --no-tools. A reviewed branch that ships a .omp/tools/*.ts file would run during the review.
  • Run omp from an isolated sandbox directory (see "Report-Only Sandbox" below) whenever the reviewed content is untrusted. Project-level custom-tool discovery (<cwd>/.claude/tools, <cwd>/.omp/tools) is keyed to omp's cwd, so a throwaway cwd outside the repo starves the untrusted repo's own tools — that closes the main vector (a reviewed branch shipping its own .omp/tools/*.ts, which would run at import() time with no model involvement). Attach the real files by absolute @path. Caveat: user-level tools (~/.claude/tools, ~/.omp/plugins/*) resolve from $HOME, not cwd, so the sandbox does not starve them — see "What the sandbox does and doesn't cover" below.
  • Attach files by writing @path inside the prompt; each referenced file's contents are read into the message context. Multiple @path tokens (and multi-line prompts) work. Use absolute paths so attachment still works from the sandbox cwd. Quote any mention that interpolates a path@\"$repo/file\" — because omp's unquoted-mention parser stops at the first space ([^\s@]+), so an absolute path containing a space (e.g. a repo under /Users/me/My App) is truncated and the file is silently skipped.
  • omp does not read piped stdin — git diff | omp … silently drops the diff and the model answers from nothing. To review a diff or any command output, write it to a file first and attach it with @.

Read the full file on GitHub · 240 lines

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.

  1. 10d ago First seen · 240 lines · 384 tokens per session scan C b746bc048165

Subscribe to this mod's changes

kimi-consultant is an agent published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 4d ago), licensed MIT. It adds 384 tokens to every session and 3,045 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

ai-eval-engineer

Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.

avelikiy/great_cto · 71 tokens

data-platform-reviewer

Data-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off retention + lineage decisions before senior-dev claims tasks.

avelikiy/great_cto · 33 tokens

mlops-reviewer

MLOps / model lifecycle pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off training-pipeline + serving-strategy decisions before senior-dev claims tasks.

avelikiy/great_cto · 41 tokens

auth-engineer

Authentication and access-control specialist for SMB Product-Builder products. Owns the auth contract — provider choice (Auth.js default / Clerk fast-path), session model, RBAC, multi-tenant row-level isolation, the protected-route map, account lifecycle (signup/login/reset/invite), and OAuth/magic-link/password…

avelikiy/great_cto · 86 tokens

geo-routing-engineer

Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…

avelikiy/great_cto · 112 tokens

us-ai-reviewer

US AI-governance pre-implementation reviewer — the US analogue of the EU AI Act coverage. Outputs threat model TM-usai-{slug}.md and signs off the AI-governance gate before senior-dev claims tasks.

avelikiy/great_cto · 50 tokens