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 Rosenfan/Matrix --skill matrixgit clone --depth 1 https://github.com/Rosenfan/MatrixWrote 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/rosenfan/matrix/matrix)<a href="https://agentmods.dev/skills/rosenfan/matrix/matrix"><img src="https://agentmods.dev/badge/skills/rosenfan/matrix/matrix/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/rosenfan/matrix/matrix"><img src="https://agentmods.dev/badge/skills/rosenfan/matrix/matrix.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 | $0.00017 | $0.01655 |
| Opus 5.5 | $0.00007 | $0.00662 |
| Sonnet 5.5 | $0.00003 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00166 |
Grade A, and why
matrix 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 28d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matrix
以当前仓库的 .matrix/ 为唯一状态来源；不得从聊天记录推断阶段。
读取 node <matrix-skill-directory>/scripts/matrix-runtime.mjs inspect 的 artifact_language。规范 Markdown 标题 token 必须保持不变；面向用户的产物正文、说明和 handoff 在 zh-CN 时写中文，在 en 时写英文。
所有 workflow 命令都先执行当前项目 Matrix Skill 自带的 Runtime，使项目兼容性权威优先于不同版本的全局启动器：
node <matrix-skill-directory>/scripts/matrix-runtime.mjs inspect
全局 matrix 命令只负责 init、update 和 bootstrap。受信任的 0.1.4 启动器只会自动委派给版本与 hash 都精确匹配的 0.1.4 项目 Runtime。项目 Runtime 属于不同版本或无法识别版本时仍是项目权威，但必须执行启动器返回的精确直连命令；旧版启动器不具备这项跨版本检查，不能作为项目 workflow 入口。
有活动变更时，报告其 phase、冻结的 orchestration 以及 Arch 安装完整性，再按 Runtime 结果进入 next_skill。没有活动变更时，为开发请求创建简短 kebab-case ID：
node <matrix-skill-directory>/scripts/matrix-runtime.mjs init <change-id> --workflow <full|hotfix|tweak> --orchestration <prim|arch> --title "<title>"
显式模式优先，否则使用项目 default_orchestration。解析后的模式在整个 change 生命周期中不可切换。
编排模式
- Prim：各阶段使用 Matrix 自身能力，不依赖 Matt Skills。
- Arch：仅在任务事实满足触发条件时，调用活动 Change 冻结的十项自动能力。Matrix 0.1.4 审查 Matt Skills v1.2.3 官方 25 项角色，只把其中 23 项兼容 Skill 安装在项目本地；排除
implement与 rawresolving-merge-conflicts。
两种编排模式使用已选定的 workflow profile：full 走 open → design → build → verify → archive；hotfix 与 tweak 共用内部 lightweight profile，走 open → build → verify → archive，仅证据策略不同。Arch 能力不得写 Matrix 状态、推进阶段、提交、归档或创建竞争工作流。
正确安装的 Arch 能力执行失败时，最多允许一次同能力的 Matrix fallback，并记录失败与证据。缺失、修改或不完整的 Arch 安装必须通过 matrix init --with-mattpocock 修复，不得切换活动 change 到 Prim。
恢复
只能通过 Runtime 恢复，不得手工修改状态：
node <matrix-skill-directory>/scripts/matrix-runtime.mjs return design --reason design-gap
node <matrix-skill-directory>/scripts/matrix-runtime.mjs return build --reason verification-failed
node <matrix-skill-directory>/scripts/matrix-runtime.mjs return design --reason acceptance-or-design-gap
node <matrix-skill-directory>/scripts/matrix-runtime.mjs abort --reason <requirement-cancelled|superseded|no-longer-valuable|blocked|other>
Return 会把当前 verification.md 轮换至按 revision 编号的证据历史。Archive 等待确认期间若验收或设计改变，只能使用 archive -> design 的 acceptance-or-design-gap Return。Abort 将终态变更移入 .matrix/archive/，但不会撤销工作区代码。
What ships with it
5 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.
- 28d ago Changed · +1 lines 4f2e45c8490d
- 29d ago Changed · -4 lines · -19 tokens per session scan B → A bb666ea09807
- 1mo ago Changed · -5 lines scan A → B 9cc0ef9d7f40
- 1mo ago First seen · 93 lines · 36 tokens per session scan A 76a7586052cc
matrix is a skill published in the GitHub repository Rosenfan/Matrix (5 stars, last pushed 29d ago), licensed MIT. It adds 17 tokens to every session and 1,655 once invoked, about $0.0001 per session on Opus 5.5. 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
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.