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 matrix-handoffgit 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-handoff)<a href="https://agentmods.dev/skills/rosenfan/matrix/matrix-handoff"><img src="https://agentmods.dev/badge/skills/rosenfan/matrix/matrix-handoff/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-handoff"><img src="https://agentmods.dev/badge/skills/rosenfan/matrix/matrix-handoff.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 | $0.00042 | $0.00959 |
| Opus 5.5 | $0.00017 | $0.00384 |
| Sonnet 5.5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
matrix-handoff 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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matrix Handoff（Implementation Handoff）
这是可选旁路，不是 Matrix phase。它不得执行 transition、archive，也不得写入 matrix.yaml 或 events.jsonl。它只支持匹配的 full 或 legacy-full 三产物 Contract；新的 lightweight hotfix/tweak 不支持导出。
人类可读 handoff 内容使用 inspect 的 artifact_language；稳定的机器可读标题和 metadata key 保持不变。
何时使用
满足以下条件时使用 $matrix-handoff：
- 变更已进入 Build，且
design -> build已批准精确 Contract； - 你希望由另一个 agent 实现冻结的设计——例如 Codex 设计、Claude Code 实现，或 zcode 设计、opencode 实现；
- 你需要一份带全部实现细节的有界任务包。
前置条件
导出器写任何内容前先做只读检查：
node <matrix-skill-directory>/scripts/matrix-runtime.mjs guard build
若结果为 CONTRACT_CHANGED、CONTRACT_UNAPPROVED 或 CONTRACT_READ_FAILED，回到 $matrix-design，修订后重新进入 Build 取得新批准。导出只读取批准快照中的 proposal.md、design.md 与 plan.md。
导出
实现 agent 由用户显式选择，通过 --agent <agent-id>（kebab-case）传入；可用 --from <agent-id> 标注设计方 agent。
# 通用 agent 交接：写入 artifacts/handoff-task-<ID>.md
node <matrix-skill-directory>/scripts/matrix-runtime.mjs export --task-id <ID> --agent opencode
node <matrix-skill-directory>/scripts/matrix-runtime.mjs export --task-id <ID> --agent claude-code --from codex
# 兼容形态（Claude Code）：写入 artifacts/claude-task.md
node <matrix-skill-directory>/scripts/matrix-runtime.mjs export --task-id <ID> --target generic
# FnSec：仅在 active.md 含有 NO_ACTIVE_OBJECTIVE 时更新看板
node <matrix-skill-directory>/scripts/matrix-runtime.mjs export --task-id <ID> --target fnsec --apply-fnsec-board
--agent 与 --target 互斥。新交接推荐 --agent；--target generic 仅为兼容保留。
任务包内容
导出包（artifacts/handoff-task-<task-id>.md）的元数据记录 Implementation actor（--agent 值）与 Decision owner（--from 值，缺省为 "Matrix change owner"），并包含批准的 Contract hash 与 revision，以及同一冻结快照的 proposal、design、plan。Objective、Allowed/Prohibited work 与 Stop conditions 原样携带——它们与具体 agent 无关。
实现 agent 完成后
继续 $matrix-verify 前先核对以下证据：
-
artifacts/verification.md存在且含## Build evidence - Build evidence 含具体命令与结果
- plan 的 Validation 命令全部执行
-
NEEDS_DECISION项已解决或已记录
证据缺失时，让实现 agent 补齐后再继续。
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.
- 10d ago First seen · 80 lines · 42 tokens per session scan A 7541fe0315c7
matrix-handoff is a skill published in the GitHub repository Rosenfan/Matrix (5 stars, last pushed 11d ago), licensed MIT. It adds 42 tokens to every session and 959 once invoked, about $0.0002 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 2026-09-20.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…