A command that sends large codebase investigations or major refactoring tasks to the Kimi Code command-line tool, then reviews the resulting changes.

Use it for large repositories, multi-file implementations, and extensive refactors. It can also delegate in read-only mode for exploration without writing changes.

It helps handle work that may span many files or require extensive repository exploration, while keeping a review step before accepting the result.

kimi — Command for Claude Code by pwdev-solucoes

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 pwdev-solucoes/pwdev-claude-marketplace

Claude Code

/plugin install pwdev-code

Made for: Claude Code.

Or install pwdev-code, the plugin that ships this one along with the rest of its 2 skills, 22 commands, 8 agents, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/kimi/github.svg)](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/kimi)

Your own site

<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/kimi"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/kimi/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/kimi"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/kimi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 961 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00961
Opus 5	$0.00011	$0.00481
Sonnet 5	$0.00004	$0.00192
Haiku 4.5	$0.00002	$0.00096

Measured 9d ago against content hash 36c86abe5d2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

kimi scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

(`curl -LsSf https://code.kimi.com/install.sh | bash`, then run `kimi` and

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(`curl -LsSf https://code.kimi.com/install.sh | bash`, then run `kimi` and

plugins/pwdev-code/commands/kimi.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pwdev-code:kimi — Delegate to Kimi Code CLI

Role

Orchestrator: sends the task to the external Kimi Code CLI via the standardized delegation script, then performs a MANDATORY critical review. Best for: large repos, multi-file implementations, extensive refactors (long-context exploration). Protocol details: ${CLAUDE_PLUGIN_ROOT}/references/delegation.md

CLI note

Newer Kimi versions accept --quiet --prompt "<prompt>"; older ones take the prompt positionally. The script auto-detects via kimi --help — no action needed here.

Input

$ARGUMENTS: the task description. --read-only → MODE=read (default: write).

Flow

STEP 0 — Language

Follow ${CLAUDE_PLUGIN_ROOT}/references/language.md (resolve lang from .planning/config.json; ask only if unset).

STEP 1 — Preflight

Parse $ARGUMENTS: strip --read-only (→ MODE=read); the remainder is the task. Empty task → show usage and STOP.
git status --porcelain — if the tree is dirty in write mode, warn the user that delegation results will be hard to attribute; offer to continue or abort.
Record baseline: git rev-parse HEAD and git status --short.

STEP 2 — Human Confirmation (same rule as review.md STEP 3.5)

Show the EXACT command that will run:

"${CLAUDE_PLUGIN_ROOT}/scripts/run-agent.sh" kimi <write|read> "<task>"

If this is the FIRST external CLI run in this session → require explicit confirmation before executing. Never proceed silently.

STEP 3 — Run

Execute the command via Bash with a tool timeout ≥ the script timeout + 60s. Extensive refactors are slow — consider external_models.kimi.timeout_s: 900 or higher (default 600s).

exit 127 → Kimi not installed (curl -LsSf https://code.kimi.com/install.sh | bash, then run kimi and /login once); STOP.
exit 124 → report the timeout; suggest raising external_models.kimi.timeout_s.
exit 4 → another write delegation is running; wait for it.
Output copy (when .planning/ exists): .planning/delegation/<ts>-kimi.md

Read the full file on GitHub · 91 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.

9d ago First seen · 91 lines · 22 tokens per session scan C 36c86abe5d2a

Subscribe to this mod's changes

kimi is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 961 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

kimi