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 linxule/kimi-plugin-cc --skill kimi-swarm-writegit clone --depth 1 https://github.com/linxule/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/linxule/kimi-plugin-cc/kimi-swarm-write)<a href="https://agentmods.dev/skills/linxule/kimi-plugin-cc/kimi-swarm-write"><img src="https://agentmods.dev/badge/skills/linxule/kimi-plugin-cc/kimi-swarm-write.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 2 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00051 | $0.00612 |
| Opus 5 | $0.00026 | $0.00306 |
| Sonnet 5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
kimi-swarm-write 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 8d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kimi Swarm Write
Forward this request to the local kimi-code companion runtime by shell. Do not use MCP for this skill.
Invocation
- Resolve the plugin root: prefer
$PLUGIN_ROOTif the host sets it; otherwise use the directory that CONTAINS theskills/directory (i.e. two levels up from thisSKILL.md). - Sanity check:
<plugin-root>/scripts/companion.shmust exist — it is the bundled entrypoint that resolves Node and runs the compiled runtime from<plugin-root>/dist/. - Launch the shell command from the user's current workspace directory so
scripts/companion.shcaptures the intended workspace cwd. - Run:
PLUGIN_ROOT="<plugin-root>" "<plugin-root>/scripts/companion.sh" task swarm --write <args> - If the plugin host provides
PLUGIN_DATAinstead ofCLAUDE_PLUGIN_DATA, the shell wrapper exports the Claude-compatible alias for the runtime. If neither is set, the wrapper uses a Codex data directory under$CODEX_HOME/plugins/data/kimi-marketplace-kimi,~/.codex/plugins/data/kimi-marketplace-kimi, or/tmp/kimi-plugin-cc-codex-data/kimi-marketplace-kimiin a fully sanitized environment.
Arguments
Pass through: [--budget <30m|1h>] [--cap <N>] [--max-concurrency <N>] [-m <model>] <objective>
Handling
- Require both many disjoint write targets and explicit parallel fan-out intent.
- Keep
--max-concurrencyconservative, normally 1, unless the user explicitly asks to widen it. - The runtime rejects
--background, but detaching your own shell call is expected: a fan-out routinely outlives a foreground timeout, and the run is patch-only and worktree-confined. Keep--budgetand--max-concurrencyfinite. To stop a run, usecompanion.sh cancelwith NO id — it targets the latest running job for the repo, and no UUID crosses you or the user (a detached run prints nothing at launch; the id first arrives with the final report). Prefer that over an interrupt: an interrupt gives the companion only ~1.35s before SIGKILL, less than its teardown plusgit diff --binarypatch capture, so interrupting can lose the patch. - If the companion reports SWARM_HOOK_NOT_INSTALLED, tell the user to run Claude Code /kimi:setup or Codex $kimi-setup, then retry.
- Return the patch path and companion output verbatim; do not apply the patch unless the user separately asks.
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.
- 8d ago First seen · 29 lines · 51 tokens per session scan A 254aedfc0780
kimi-swarm-write is a skill published in the GitHub repository linxule/kimi-plugin-cc (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 612 once invoked, about $0.0003 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
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
pr-feedback
Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.
detect-task
Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
loop-bb-pr
A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.