Static plugin payloads for Grok Build, Codex, Kimi Code CLI, and a dependency-free bootstrap for OpenCode. Register one repo, install what you need, ship.
$ grok plugin marketplace add VeigaPunk/ds4cc-marketplace
Live terminal. Four hosts, one repo. Commands below are the real install paths — outputs are representative.
click a host to replay its install sequence · sound off, green on
Every plugin ships an actionable SKILL.md (fenced commands, no boilerplate) and passes the Rust validator. Filter by name or capability.
A compact Rust dashboard that renders every live tmux pane side by side, preserving terminal color while keeping each pane’s newest output line anchored at the bottom.
┌ attached · build ────────┐ │ compiling renderer │ │ running regression suite │ │ │ │ │ │ │ │ │ │ 68 passed; 0 failed │ └──────────────────────────┘
Blank interior rows remain blank above the content. The last retained output line sits directly above the lower border, so the current result is visible at a glance.
Use the standalone TUI or feed Pango JSON into Waybar. The renderer keeps the existing 130px bar height, JetBrains Mono metrics, and native polling setup.
Use the supported flow for your host; review third-party plugin sources before installation.
$ grok plugin marketplace add VeigaPunk/ds4cc-marketplace $ grok plugin list --available --json $ grok plugin install myagents --trust $ grok plugin enable myagents
# install the core set in one loop
grok plugin install "$p" --trust && grok plugin enable "$p"
done
Non-CLI fallback: paste GROK_PASTE.md into a Grok chat. This is separate from the Grok Build CLI flow above.
$ codex plugin marketplace add VeigaPunk/ds4cc-marketplace $ codex plugin list --available --json $ codex plugin add myagents@ds4cc --json $ codex plugin list --json
Adding a plugin installs it enabled. Start a new Codex session to load its bundled skills and tools; in the TUI, use /plugins and press Space to toggle state. Local dev checkout: codex plugin marketplace add . — the canonical manifest lives at .agents/plugins/marketplace.json.
# commands to enter in the Kimi TUI /plugins install https://github.com/VeigaPunk/ds4cc-marketplace /reload
# or register the full packaged catalog in the Kimi TUI /plugins marketplace https://veigapunk.github.io/ds4cc-marketplace/.kimi-plugin/marketplace.json /plugins install <artifact-url-or-local-path> /reload
Invoke as /skill:<skill-name> and /<plugin>:<command>. Third-party installs ask for trust first — review before approving.
$ git clone https://github.com/VeigaPunk/ds4cc-marketplace.git $ node ds4cc-marketplace/scripts/install-opencode-agents.mjs --global # or: --project /path/to/project
Writes 15 the-* agents plus the-netsshark (16 subagents total), and a separate orch primary mode.
A read-only Apps SDK wrapper exposes a reviewed subset of the catalog through a production MCP endpoint with an embedded catalog widget.
› https://app.ds4cc.com/mcp
Scoped to an explicitly reviewed, read-only tool surface with required annotations and widget CSP/domain metadata. It is not the public 16-plugin marketplace.
| privacy | app.ds4cc.com/privacy |
|---|---|
| terms | app.ds4cc.com/terms |
| support | app.ds4cc.com/support |
| health | app.ds4cc.com/health |
A binary crate (ds4cc-validator) gates every plugin on structure, schema, and skill actionability. CI runs it on each push.
$ cargo run --manifest-path marketplace/validator/Cargo.toml -- marketplace Validation passed. $ cargo test --manifest-path marketplace/validator/Cargo.toml test result: ok. all green
marketplace/ (web/CI) and repo root (canonical Codex layout at
.agents/plugins/marketplace.json) both validate.
./plugins/<name>.codex-plugin/plugin.json, name matches entryX.Y.Zskills/ + README.md presentDS4CC keeps the strongest entry per domain and updates the reviewed set as better evidence emerges. Full policy in CURATION.md.
Comparative, compatibility, price, and “full functionality” claims require a dated evidence packet: tested hardware/software, comparison baseline, known limitations, repeatable demo.
Mirrored from the packaged SSoT (marketplace/plugins/xbrd-gdsp-fknpft/commands/references/xbreed-shared.md). If this section and the SSoT disagree, the SSoT wins and this section is drift.
the-judge fable 5 · xhigh the-planner sonnet · medium the-scout sonnet · medium the-reviewer sonnet · medium the-labrat sonnet · medium the-executor sonnet · medium the-connector sonnet · medium the-distiller sonnet · medium the-simplifier sonnet · medium the-revenger sonnet · medium the-sentinel sonnet · medium the-critic sonnet · medium the-mutation-tester sonnet · medium the-scribe sonnet · medium the-netsshark host extension
planner wwkd · native scout / labrat / executor xask --spark --gs codex → gpt-5.4-mini reviewer xask --gpt55 --gs -e low codex → gpt-5.6-sol critic Layer-0: heuer-planning → xask --gpt55 --gs -e low codex → gpt-5.6-sol revenger RECON xask --gpt55 --gs -e high codex → gpt-5.6-sol sentinel xask --gpt55 --gs -e low codex → gpt-5.6-sol connector xask --spark codex · no --gs mutation: single / <=4 xask --spark --gs codex mutation: >=5 / breadth xask --effort high --gs codex distiller / simplifier / scribe native
xask gemma (aliases g, legacy gemini) dispatches through xbreed ask gemma → gemma-hvm → run.sh/run-hvm4.sh → Bend 0.2.38 gen-hvm → HVM4 4.0 control gate → Ollama. Default model gemma4:26b via HVM_GEMMA_MODEL. Cloud Gemini CLI is retired — do not call the gemini binary. Connector and any g-* teammates MUST use this lane for cross-model breadth.
Ollama/Gemma 4 is the serving substrate. HVM4 controls routing only; tensor inference is not claimed to run in HVM4.