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/rosenfan/matrix/matrixnpx skills add Rosenfan/Matrix --skill matrixgit clone --depth 1 https://github.com/Rosenfan/MatrixWhat 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 | $0.00036 | $0.01197 |
| Opus 5 | $0.00018 | $0.00598 |
| Sonnet 5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matrix
Use Matrix as the development-workflow entrypoint. Its source of truth is the current repository's .matrix/; never infer a phase from chat history.
Read artifact_language from matrix workflow inspect. Keep required Markdown heading tokens unchanged, but write every user-facing artifact body, explanation, and handoff in that language: English for en, Chinese for zh-CN.
Route
First run:
matrix workflow inspect
If and only if the matrix executable is reported as absent, run the bundled fallback from this Skill directory instead:
node <matrix-skill-directory>/scripts/matrix-runtime.mjs inspect
- If an active change exists, show its phase and frozen
orchestration, report any Arch installation-integrity failure, and enter the returnednext_skillonly when the Runtime permits continuation. - If no active change exists, classify the request: reproducible small bug →
$matrix-hotfixwith workflowhotfix; bounded small change with no public API/schema/architecture impact →$matrix-tweakwith workflowtweak; otherwise full Matrix with workflowfull. - Do not create Matrix state for questions, read-only investigation, or requests outside software development.
- Before
init, derive a short kebab-case change id and an accurate title. Start withfullunless a shortcut clearly applies.
matrix workflow init <change-id> --workflow <full|hotfix|tweak> --orchestration <prim|arch> --title "<title>"
An explicit mode wins; otherwise Runtime uses the project default_orchestration. The resolved value is immutable for the change and is shown in init, inspect, and the initialized Event. Then enter $matrix-open.
Orchestration
- Prim uses Matrix's own capability in every phase and never requires Matt Skills.
- Arch conditionally invokes the initialization-verified ten-Skill cohort when documented task-fact triggers are present.
Both orchestration modes use the same selected workflow profile. full uses open → design → build → verify → archive; hotfix and tweak share one internal lightweight profile, open → build → verify → archive, with different evidence policies. Companion Skills never write Matrix state, transition, commit, archive, or create competing workflow artifacts.
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.
- 2d 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 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,197 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…