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 briandconnelly/moonbridge --skill collaborating-with-kimigit clone --depth 1 https://github.com/briandconnelly/moonbridgeWrote 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/briandconnelly/moonbridge/collaborating-with-kimi)<a href="https://agentmods.dev/skills/briandconnelly/moonbridge/collaborating-with-kimi"><img src="https://agentmods.dev/badge/skills/briandconnelly/moonbridge/collaborating-with-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.
<a href="https://agentmods.dev/skills/briandconnelly/moonbridge/collaborating-with-kimi"><img src="https://agentmods.dev/badge/skills/briandconnelly/moonbridge/collaborating-with-kimi.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 | $0.00140 | $0.02298 |
| Opus 5 | $0.00070 | $0.01149 |
| Sonnet 5 | $0.00028 | $0.00460 |
| Haiku 4.5 | $0.00014 | $0.00230 |
Grade A, and why
collaborating-with-kimi 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 11d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborating with Kimi
Use this skill as the router and shared safety contract for every Kimi workflow. Retain responsibility for the work, and compose this guidance with applicable planning, debugging, review, and verification skills instead of replacing them.
Shared workflow
- Call
kimi_statusbefore a paid call. Proceed only when bothready: trueandextra_args_valid: true. If either is false, stop and surface the corresponding readiness or operator-configuration detail. - Treat
rate_limitas unavailable, and that is not a fault. kimi exposes no quota-read channel and its provider is user-configured, sokimi_statusreportsunavailablerather than guessing. There is no quota signal to pace spend from — judge cost from the size of the task, and surface a provider-side rate-limit error (kimi_rate_limited) to the user if one comes back. - Know what the tiers do and do not guarantee before choosing one. The
kimiCLI has no sandbox and no approval prompts, so:kimi_consult/kimi_review_changesrun under a generated agent profile with no shell and no write tools. That prevents modification, NOT disclosure: Kimi's Read tool accepts absolute paths, so a prompt-injected repository can make it read other files on the machine.kimi_delegateruns with the full tool set. Its edits land in a throwaway worktree and come back as a diff that is never applied — but the worktree is not a boundary: the task can also reach the network and write outside it. The diff shows what changed in the worktree, not everything the run did.- Do not point any tier at a workspace whose contents you would not hand to the configured provider.
- Select one route below and load only its needed reference. Use a free dry-run when one exists.
- Declare the paid-call cap before the first active call, then stay within it.
- Branch on
ok, then on the concrete tool/result type. Verify claims before acting.
What ships with it
7 files 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.
- 11d ago First seen · 147 lines · 140 tokens per session scan A a6ddf51d8ab2
collaborating-with-kimi is a skill published in the GitHub repository briandconnelly/moonbridge (0 stars, last pushed 2d ago), licensed MIT. It adds 140 tokens to every session and 2,298 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
novel-game-analyze
Deconstruct a novel for game adaptation. Compress a raw novel, deconstruction library, or writing project into a SOURCEBIBLE with cited textual evidence, extracting world rules, player verbs, spaces, character will, systems, and visual anchors — without inventing a genre yet. Use for gameable book analysis, analyze a…
novel-to-game
Turn a novel into a fully playable game on the selected target platform. Orchestrates the whole adaptation pipeline — requirements intake, gameable deconstruction, concept selection, world and visual design, target-runtime build, and evidence-based QA — for a novel in any language. Use for novel to game, story to…
writing-release-notes
Use when preparing, refreshing, backfilling, or redrafting a release-notes page under docs/releases/ before opening a normal review pull request.
skills
Generate a complete SVG file from a natural language description using SEP-1577 multi-step sampling.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
researching-references
Use when a change depends on how something outside this repository actually behaves — a markdown dialect, a file format, git, a protocol, a vendor API — and docs/design/reference/ has no current reference for it, or the one it has is past its review date. Researches from primary sources and writes a dated, versioned…