Agent Plugins Marketplace
← All plugins

servo

v0.10.0

Evaluation-driven development and closed-loop quality automation for Codex

CodexClaude Code3 Skills

By ramboz1 GitHub starsUpdated last month

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
3 skill or MCP entries
Source updated
Sep 19, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install servo for Codex and Claude Code

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add servo@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/ramboz/servo

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

servo/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/content-fidelity/SKILL.md
├── skills/design-eval/SKILL.md
└── skills/eval-authoring/SKILL.md

Included Skills3

content-fidelityskills/content-fidelity/SKILL.md

Author a frozen text content-fidelity eval component for a project — the non-visual sibling of servo's design-eval. Use when generated text (a reply, a doc, a templated message) must match an intended rubric or spec ("does this text match the intended tone/content/style?") and that fidelity should drive or gate the loop. Gathers the generated text under test (file read or generator command), judges fidelity with a pinned text-capable model (n-sampled, lower-bound), freezes the definition, and installs a `score_content_fidelity` component into the project's `oracle.sh`. Do not use for deterministic checks (use scaffold-init / spec-oracle), for visual/UI fidelity (use design-eval), or for the per-iteration judge agent.

design-evalskills/design-eval/SKILL.md

Author a frozen UI design-fidelity eval component for a project — the non-deterministic sibling of servo's deterministic component templates. Use when a project must be built to match a design mockup ("does the UI match the design?") and that fidelity should drive or gate the loop. Captures app vs reference screenshots, judges fidelity with a pinned vision model (n-sampled, lower-bound), freezes the definition, and installs a `score_design_fidelity` component into the project's `oracle.sh`. Do not use for deterministic checks (use scaffold-init / spec-oracle) or for the per-iteration judge agent.

eval-authoringskills/eval-authoring/SKILL.md

Author a frozen text-judged eval from a spec-006 `residual_judgment` AC or a free-form goal. Guides triage, rubric shaping, reference-set collection, frozen n/δ/threshold/judge parameters, ADR-0024 freeze/install, and advisory judge audit. Use to author an eval, turn a goal into acceptance criteria, shape a rubric or reference set, freeze/install an eval, or audit judge trust. Do NOT use to run evals (`quality-gate`/`agent-loop`), classify deterministic checks (`spec-oracle`), decide EDD suitability (`edd-suitability`), or build design/content fidelity evals (use the `design-eval` / `content-fidelity` presets). This is the generic surface for other text-judged criteria.

Plugin manifests2

.codex-plugin/plugin.json
{
  "name": "servo",
  "version": "0.10.0",
  "description": "Evaluation-driven development and closed-loop quality automation for Codex",
  "author": {
    "name": "ramboz"
  },
  "homepage": "https://github.com/ramboz/servo",
  "repository": "https://github.com/ramboz/servo",
  "keywords": [
    "codex",
    "evaluation-driven-development",
    "quality-gates",
    "agent-loop",
    "scaffold"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "servo",
    "shortDescription": "Closed-loop evaluation and quality automation",
    "longDescription": "Servo compiles engineering intent into executable evaluation, quality gates, evidence plans, and guarded agent loops for Codex projects.",
    "developerName": "ramboz",
    "category": "Engineering",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Scaffold Servo evaluation for this project",
      "Run the Servo quality gate",
      "Create an evidence plan for this spec"
    ],
    "brandColor": "#D97706",
    "screenshots": []
  }
}
.claude-plugin/plugin.json
{
  "name": "servo",
  "description": "Closed-loop scaffolder for unattended agent operations: oracle scoring, headless agent loops, hooks, and worktree races — tailored to each project's signals.",
  "version": "0.10.0",
  "author": {
    "name": "ramboz"
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[servo on Agent Plugins Marketplace](https://pluginsmp.com/plugins/servo)