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 agentmods add skills/mateaix/matecloud/mate-preflightnpx skills add mateaix/matecloud --skill mate-preflightgit clone --depth 1 https://github.com/mateaix/matecloudWhat 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 | $0.00058 | $0.00570 |
| Opus 5 | $0.00029 | $0.00285 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
mate-preflight 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 2d 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.
What it actually says
提交 / PR 前自检
目标：让每次提交都过得了 harness，并符合提交规范。
第一步：跑约束校验
bash .claude/.harness/checks/run-all.sh
- 阻断级（竞品名 / 硬编码密钥 / OSS 边界 / 领域纯净）任一红 → 必须修到绿才提交。
- 告警级（MapStruct / AutoConfig / Flyway）→ 看是不是你这次引入的；是就一并修， 历史存量可暂留但别新增。
修法对照 .claude/.harness/rules/：每个 check 的 rule: 字段（见 manifest.yml）指向对应规则文件。
第二步：范围自查（别捎带无关改动）
git status --short
git diff --cached --stat
只暂存本次任务相关文件。不要顺手提交他人工作区改动、docs/tasks/（含内部路径）、
或 .claude/ 下除 .harness 外的本地配置。
第三步：提交信息规范
格式 {type}({scope}): {description}，中文描述 OK：
- type：
feat/fix/refactor/docs/chore/test/style/perf - scope：模块名（
system/auth/gateway/harness…） - 示例：
fix(system): 用户查询分页参数校验缺失
提交信息末尾按本仓约定加 Co-Authored-By 行（若由 AI 协作）。
第四步：分支
当前在默认分支（main）就先开 feature/{name} 或 fix/{issue}；
本项目日常工作流是提交并推送到 dev（除非另有要求）。
一键清单
-
run-all.sh阻断级全绿 - 未新增告警级违规
- 暂存范围干净，无无关文件 / 内部路径
- 提交信息
{type}({scope}): ...
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.
- 2d ago First seen · 52 lines · 58 tokens per session scan A 28ac85fc8128
mate-preflight is a skill published in the GitHub repository mateaix/matecloud (1,693 stars, last pushed 3d ago), licensed Apache-2.0. It adds 58 tokens to every session and 570 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
obsidian-writer
Write well-formatted notes to the atmosphere-vault Obsidian knowledge base. Use this skill whenever creating or updating an ADR, runbook, plan, API doc, guide, session output, or any structured document that should land in the vault — even when the user doesn't say "Obsidian" explicitly. Delegates to…
obsidian-vault-setup
Use when setting up the shared atmosphere-vault Obsidian vault on a new machine or for a new team member. Guides through cloning, symlinking claudedocs, and verifying obsidian-cli.
llm-judge
AI quality judge that scores agent responses 0-10 across helpfulness, accuracy, completeness, and clarity. Use when evaluating multi-agent output or implementing LLM-as-judge quality gates.
rocketmq-rust-issue-generator
Use when the user asks to create, draft, prepare, or publish a GitHub issue for the rocketmq-rust project — bugs, features, enhancements, refactors, docs, unit tests, CI, runtime-model, broker, namesrv, client, store, dashboard, architecture, or performance work — especially when the issue must preserve real…
rust-doc-comment-generator
Generate idiomatic, production-grade Rust comments and documentation strictly following official Rustdoc and Rust API documentation conventions. Designed for real-world Rust projects with zero AI-identifiable markers.
translate-it-doc-en-zh
Translate English IT and software engineering documents into professional, accurate Chinese. Use when user provides English technical documentation, API docs, README, design docs, RFCs, or source code comments and asks for Chinese translation. Prioritize correctness, standard IT terminology, and engineering-style…