项目文件夹

文件
Seth Hobson be57c0b2e3 feat: multi-harness plugin marketplace (Codex, Cursor, OpenCode, Gemini) (#541)
* feat(adapters): multi-harness framework + harness_portability eval dimension

Turn this Claude Code plugin marketplace into a generic agentic-harness
marketplace. Adapters under tools/adapters/ emit harness-native artifacts
for OpenAI Codex CLI, Cursor, OpenCode, and Gemini CLI from a single
Markdown source. Source-of-truth stays under plugins/ — Claude Code is
unchanged.

Framework (tools/adapters/):
- base.py — PluginSource parser, HarnessAdapter ABC, write/mirror helpers
  (path-traversal guard, UTF-8-safe), inline-list + block-list + block-scalar
  YAML-ish parser, _utf8_safe_cut, _split_inline_list, _normalize_author
- capabilities.py — per-harness capability matrix, TOOL_NAME_MAPS,
  MODEL_ALIASES, resolve_model() with explicit warnings
- codex.py — emits .codex/{skills,agents}/ + AGENTS.md (≤150-line
  table-of-contents). Fence-aware body splitter, _utf8_safe_cut for
  multibyte safety, _yaml_scalar with reserved-word + special-char quoting.
  Skill/command name collision detection (and second-order __cmd fallback).
- cursor.py — emits .cursor-plugin/{plugin,marketplace}.json + curated
  .cursor/rules/*.mdc. _validate_mdc_frontmatter handles YAML block scalars
  (no false positives on colons in description body). _normalize_author
  handles dict, npm-style strings, and author lists.
- opencode.py — transpiles agents to .opencode/agents/<id>.md with
  mode:subagent + permission: deny-everything-else block (skill/task always
  allowed as base capabilities — Claude's implicit defaults).
- gemini.py — emits native skills/, agents/, and commands/ at extension
  root (April 2026 spec). Tool-allowlist remapped via TOOL_NAME_MAPS.

CLI + tooling:
- tools/generate.py — unified `make generate HARNESS=<x> [PLUGIN=<y>]`,
  with --clean (containment-guarded; case-insensitive on Darwin/Win32),
  --prune (orphan removal across all per-harness output trees), --strict
  (warnings fail), per-plugin error aggregation, refuses --clean --plugin
  (would silently wipe other plugins' artifacts).
- tools/validate_generated.py — structural validation across all four
  harness outputs. Codex 8KB cap → error. _extract_permission_block
  correctly handles nested permission keys (column-0 only).
- tools/doc_gardener.py — recurring drift detection per OpenAI harness-
  engineering principle. STALE_ARTIFACT (info), DEAD_LINK (error),
  MARKETPLACE_ORPHAN (error), SKILL_OVER_CODEX_CAP (warning), grouped
  output sorted by severity.

plugin-eval (extends existing framework):
- New harness_portability dimension (6% weight, rebalanced from existing
  static sub-scores). Surfaces non-portable patterns with concrete
  remediation hints: SKILL_OVER_CODEX_CAP, CLAUDE_TOOL_REFS,
  CLAUDE_TOOL_PROSE, AGENT_NAME_COLLISION, BARE_MODEL_ALIAS.
- _CAMEL_TOOL_PATTERN requires Claude-tool context (no false positives
  on Rust's `Task` etc.). _TOOL_PROSE_PATTERN case-sensitive on tool
  names, case-insensitive on the leading article.
- Findings do NOT also feed anti_pattern_penalty (no double-counting).

Documentation:
- Top-level guides: CODEX.md, CURSOR.md, OPENCODE.md (≤150 lines each,
  table-of-contents pattern per OpenAI harness-engineering post)
- docs/harnesses.md — capability matrix, graceful-degradation table,
  generated output paths
- docs/authoring.md — portable-content style guide (tools, models,
  collision rules, fence-respect)
- docs/round-trip-results.md — real-CLI verification recipes (OpenCode
  discovers 193 subagents, Gemini extensions validate passes, Codex
  TOMLs all parse)
- CONTRIBUTING.md — new file pointing at docs/authoring.md
- README.md — rewritten for multi-harness (145 lines, was 460)
- CLAUDE.md — trimmed to 60-line table-of-contents
- GEMINI.md — trimmed from 1500 to 500 tokens (3× over budget previously)

Tests: 181 passing (103 plugin-eval + 78 tools/tests). Real-CLI round-trip
verified for OpenCode, Gemini, and Codex (TOML parses).

Replaces tools/generate_gemini_commands.py with the unified CLI.

* refactor(skills): extract detail to references/details.md (~75 skills)

Apply Anthropic's canonical SKILL.md progressive-disclosure pattern across
the marketplace: SKILL.md body becomes a navigation tier (trigger phrasing
+ quick start), detailed templates and worked examples move to
references/details.md (loaded on demand by the agent).

Motivation: OpenAI Codex CLI hard-truncates skills at 8 KB. Before this
change, ~90 skills exceeded that cap and would silently break on Codex.
The progressive-disclosure pattern is also Anthropic's documented
recommendation for token efficiency — Claude Code reads references/ files
on demand when the body navigation says to.

What's extracted, by pattern:
- Pass 1 (## Templates section): 19 skills — full template libraries
  moved to references/details.md
- Pass 2 (## Implementation Patterns / ## Advanced Patterns): 13 skills
- Pass 3 (everything between nav-tier and wrap-tier headings): 53 skills
- Conservative re-extraction for 8 skills that got over-reduced — kept
  ~6-7 KB inline (most of the quick-start tier) plus references/ overflow

What stays inline (SKILL.md navigation tier):
- description: frontmatter (triggering — unchanged for all skills)
- ## When to Use This Skill / ## Core Concepts / ## Quick Start
- ## Best Practices / ## Troubleshooting / ## See Also wrap-ups
- A pointer note ("see references/details.md") so the agent knows where
  to look for detail

What goes to references/details.md (detail tier, on-demand load):
- ## Templates (full code template libraries)
- ## Implementation Patterns / ## Advanced Patterns (deep examples)
- Mid-skill walkthroughs that exceed the inline budget

Also in this commit:
- plugins/brand-landingpage description trimmed from 958→543 chars
  (preserves trigger phrasing, drops verbose example-quote list)

Net effect:
- SKILL_OVER_CODEX_CAP findings: 90 → 10 (88% reduction)
- All triggers unchanged — discovery behavior identical across harnesses
- 75 new references/details.md files with the extracted content
- Same depth of guidance, loaded progressively

Remaining 10 oversized skills are complex multi-section docs (e.g.
postgresql, code-review-excellence, evaluation-methodology) that need
per-skill manual judgment — flagged by `make garden` for future work.

* chore: bump all plugin versions (multi-harness release)

Patch-bump every local plugin (81) in both .claude-plugin/marketplace.json
entries and each plugins/<name>/.claude-plugin/plugin.json. Minor-bump the
top-level marketplace metadata.version (1.6.0 → 1.7.0) to signal the
multi-harness adapter framework addition.

The external git-subdir entry (qa-orchestra) is unaffected — its version
is governed by its upstream repo.

* fix(opencode): preserve explicit tools:[] + word-boundary subtask match

Addresses two Codex review findings on PR #541.

## P1 — `tools: []` silently upgraded to permissive (privilege escalation)

Before: `_build_permission_block` returned `{}` for any empty list, which
omits the `permission:` block entirely from the emitted agent. An author
who explicitly wrote `tools: []` to lock down an advisory-only agent got
an UNRESTRICTED agent in OpenCode. Affected agent in this tree:
`plugins/arm-cortex-microcontrollers/agents/arm-cortex-expert.md`.

Fix: `_build_permission_block` now takes a `has_tools_field` flag so the
caller can distinguish "tools: key missing" (Claude default permissive)
from "tools: []" (explicit lock-down). The lock-down case emits a
deny-everything block that allows ONLY the base capabilities (skill, task)
that Claude Code always grants implicitly. Verified against the real
arm-cortex-expert agent — now emits read/edit/write/bash/grep/glob/list:
deny, task/skill: allow.

## P2 — `"agent" in cmd.body.lower()` false-positives on substrings

Before: a command body containing `PerformanceReviewAgent` (class name
in a code snippet) or `useragent` triggered `subtask: true`, changing
runtime behavior based on incidental text.

Fix: switch to a compiled word-boundary regex `\b(agent|subagent)s?\b`
(case-insensitive). Tests confirm the substring `PerformanceReviewAgent`
no longer fires, while a real "spawn a subagent" sentence still does.

## Tests

3 new regression tests in tools/tests/test_adapters.py:
- `test_explicit_empty_tools_yields_locked_permission_block` (P1)
- `test_missing_tools_field_yields_no_permission_block` (P1 boundary)
- `test_subtask_inference_word_boundary` (P2)

184 total tests pass (was 181). OpenCode round-trip still discovers all
193 subagents; arm-cortex-expert agent is now properly locked down.

* test: behavioral verification + CI gates for multi-harness pipeline

Adds three layers of automated verification that pure-Python parser tests
miss, plus the CI jobs that turn them into hard gates. Catches the kinds
of issues that previously only surfaced when a real user installed the
marketplace and tried to use it.

## test_real_world.py — real-source structural tests

Runs against the actual `plugins/` tree (not synthetic fixtures). Catches
issues that only appear on real content:

- every marketplace entry resolves to a plugins/<name>/ dir
- every local plugin dir appears in marketplace.json
- marketplace.json version == per-plugin plugin.json version (catches drift)
- every plugin loads via load_plugin() without error
- no plugin name contains `__` (adapter namespace separator)
- every agent has name + description; every skill has a trigger phrase
  (same regex plugin_eval's MISSING_TRIGGER check uses)
- no agent name collides with Codex built-ins
- every refactored skill (with `references/details.md`) has:
  - meaningful detail content (>=500 B in details.md)
  - a pointer to references/ in the SKILL.md body
  - a navigation-tier heading preserved (When to Use, Overview, etc.)
  - body >= 600 B (not a stub)
- every plugin.json has name + version matching the dir

This test pass found and fixed three real defects before commit:
- ship-mate/skills/scan: description had no trigger phrase ("Use when…")
- reverse-engineering/skills/memory-forensics: nav-tier section lost
  during extraction
- reverse-engineering/skills/binary-analysis-patterns: same

All three are now fixed (preserved trigger phrasing, added When-to-Use
sections back to the skills my extraction over-trimmed).

## test_round_trip.py — generate→parse→verify

CI runs this AFTER `make generate-all`. Catches generation-time regressions:

- OpenCode/Codex/Gemini agent counts match source agent count (no skips)
- every Codex SKILL.md under 8 KB (the cap that would silently truncate)
- every Codex agent TOML has required fields + valid sandbox_mode
- every OpenCode agent has mode in {primary,subagent,all} and
  provider-prefixed model
- locked agents (source `tools: []`) emit proper deny-everything permission
  block with skill/task allow (regression guard for PR-541 P1)
- every Gemini @{path} injection resolves to a real source file
- every Gemini command TOML has prompt + {{args}} placeholder
- every context file (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) within
  150-line cap
- Cursor marketplace + per-plugin manifests cover all local plugins
- .cursor/rules/*.mdc only use the 3 documented frontmatter keys

## test_cli_smoke.py — real-CLI subprocess tests

Invokes the actual harness binaries (OpenCode, Gemini, Codex, Claude Code)
against the generated artifacts. Catches CLI-level issues pure-Python
parsing can't see: schema-loader drift, plugin-discovery bugs, version
incompatibilities.

- `opencode agent list` — must succeed AND discover every source agent
  (currently 191 + 2 OpenCode built-ins)
- `gemini extensions validate <repo>` — must return success
- `codex doctor` — must report healthy install
- every Codex agent TOML must parse with stdlib `tomllib`
- `claude --version` — sanity check the Claude Code CLI loads
- marketplace.json must have owner + metadata.version for Claude Code's loader

Per-CLI tests skip gracefully when the binary isn't on PATH, so local
devs only exercise what they have installed. CI installs OpenCode +
Gemini and turns those skips into hard gates.

## Makefile + CI

- `make test` — full pytest suite (plugin-eval + tools/tests/)
- `make smoke-test` — generates if needed, then runs real-CLI smoke tests
- `.github/workflows/validate.yml` extended with:
  - `tools-tests` job — runs pytest tools/tests/
  - `multi-harness-generate` job — `make generate-all && make validate
    STRICT=1 && make garden`, uploads generated artifacts on every run
  - `cli-smoke-test` job — installs OpenCode + Gemini, runs test_cli_smoke.py

## Test counts

- Before: 184 tests
- After: 386 tests (parameterized real-source tests over all 82 plugins)
- All passing locally on OpenCode 1.15.7 + Gemini 0.42.0 + Codex 0.133.0
  + Claude Code 2.1.148
2026-05-22 08:18:21 -04:00

8.6 KiB

nx-workspace-patterns — templates and worked examples

Templates

Template 1: nx.json Configuration

{
  "$schema": "./node_modules/nx/schemas/nx-schema.json",
  "npmScope": "myorg",
  "affected": {
    "defaultBase": "main"
  },
  "tasksRunnerOptions": {
    "default": {
      "runner": "nx/tasks-runners/default",
      "options": {
        "cacheableOperations": [
          "build",
          "lint",
          "test",
          "e2e",
          "build-storybook"
        ],
        "parallel": 3
      }
    }
  },
  "targetDefaults": {
    "build": {
      "dependsOn": ["^build"],
      "inputs": ["production", "^production"],
      "cache": true
    },
    "test": {
      "inputs": ["default", "^production", "{workspaceRoot}/jest.preset.js"],
      "cache": true
    },
    "lint": {
      "inputs": ["default", "{workspaceRoot}/.eslintrc.json"],
      "cache": true
    },
    "e2e": {
      "inputs": ["default", "^production"],
      "cache": true
    }
  },
  "namedInputs": {
    "default": ["{projectRoot}/**/*", "sharedGlobals"],
    "production": [
      "default",
      "!{projectRoot}/**/?(*.)+(spec|test).[jt]s?(x)?(.snap)",
      "!{projectRoot}/tsconfig.spec.json",
      "!{projectRoot}/jest.config.[jt]s",
      "!{projectRoot}/.eslintrc.json"
    ],
    "sharedGlobals": [
      "{workspaceRoot}/babel.config.json",
      "{workspaceRoot}/tsconfig.base.json"
    ]
  },
  "generators": {
    "@nx/react": {
      "application": {
        "style": "css",
        "linter": "eslint",
        "bundler": "webpack"
      },
      "library": {
        "style": "css",
        "linter": "eslint"
      },
      "component": {
        "style": "css"
      }
    }
  }
}

Template 2: Project Configuration

// apps/web/project.json
{
  "name": "web",
  "$schema": "../../node_modules/nx/schemas/project-schema.json",
  "sourceRoot": "apps/web/src",
  "projectType": "application",
  "tags": ["type:app", "scope:web"],
  "targets": {
    "build": {
      "executor": "@nx/webpack:webpack",
      "outputs": ["{options.outputPath}"],
      "defaultConfiguration": "production",
      "options": {
        "compiler": "babel",
        "outputPath": "dist/apps/web",
        "index": "apps/web/src/index.html",
        "main": "apps/web/src/main.tsx",
        "tsConfig": "apps/web/tsconfig.app.json",
        "assets": ["apps/web/src/assets"],
        "styles": ["apps/web/src/styles.css"]
      },
      "configurations": {
        "development": {
          "extractLicenses": false,
          "optimization": false,
          "sourceMap": true
        },
        "production": {
          "optimization": true,
          "outputHashing": "all",
          "sourceMap": false,
          "extractLicenses": true
        }
      }
    },
    "serve": {
      "executor": "@nx/webpack:dev-server",
      "defaultConfiguration": "development",
      "options": {
        "buildTarget": "web:build"
      },
      "configurations": {
        "development": {
          "buildTarget": "web:build:development"
        },
        "production": {
          "buildTarget": "web:build:production"
        }
      }
    },
    "test": {
      "executor": "@nx/jest:jest",
      "outputs": ["{workspaceRoot}/coverage/{projectRoot}"],
      "options": {
        "jestConfig": "apps/web/jest.config.ts",
        "passWithNoTests": true
      }
    },
    "lint": {
      "executor": "@nx/eslint:lint",
      "outputs": ["{options.outputFile}"],
      "options": {
        "lintFilePatterns": ["apps/web/**/*.{ts,tsx,js,jsx}"]
      }
    }
  }
}

Template 3: Module Boundary Rules

// .eslintrc.json
{
  "root": true,
  "ignorePatterns": ["**/*"],
  "plugins": ["@nx"],
  "overrides": [
    {
      "files": ["*.ts", "*.tsx", "*.js", "*.jsx"],
      "rules": {
        "@nx/enforce-module-boundaries": [
          "error",
          {
            "enforceBuildableLibDependency": true,
            "allow": [],
            "depConstraints": [
              {
                "sourceTag": "type:app",
                "onlyDependOnLibsWithTags": [
                  "type:feature",
                  "type:ui",
                  "type:data-access",
                  "type:util"
                ]
              },
              {
                "sourceTag": "type:feature",
                "onlyDependOnLibsWithTags": [
                  "type:ui",
                  "type:data-access",
                  "type:util"
                ]
              },
              {
                "sourceTag": "type:ui",
                "onlyDependOnLibsWithTags": ["type:ui", "type:util"]
              },
              {
                "sourceTag": "type:data-access",
                "onlyDependOnLibsWithTags": ["type:data-access", "type:util"]
              },
              {
                "sourceTag": "type:util",
                "onlyDependOnLibsWithTags": ["type:util"]
              },
              {
                "sourceTag": "scope:web",
                "onlyDependOnLibsWithTags": ["scope:web", "scope:shared"]
              },
              {
                "sourceTag": "scope:api",
                "onlyDependOnLibsWithTags": ["scope:api", "scope:shared"]
              },
              {
                "sourceTag": "scope:shared",
                "onlyDependOnLibsWithTags": ["scope:shared"]
              }
            ]
          }
        ]
      }
    }
  ]
}

Template 4: Custom Generator

// tools/generators/feature-lib/index.ts
import {
  Tree,
  formatFiles,
  generateFiles,
  joinPathFragments,
  names,
  readProjectConfiguration,
} from "@nx/devkit";
import { libraryGenerator } from "@nx/react";

interface FeatureLibraryGeneratorSchema {
  name: string;
  scope: string;
  directory?: string;
}

export default async function featureLibraryGenerator(
  tree: Tree,
  options: FeatureLibraryGeneratorSchema,
) {
  const { name, scope, directory } = options;
  const projectDirectory = directory
    ? `${directory}/${name}`
    : `libs/${scope}/feature-${name}`;

  // Generate base library
  await libraryGenerator(tree, {
    name: `feature-${name}`,
    directory: projectDirectory,
    tags: `type:feature,scope:${scope}`,
    style: "css",
    skipTsConfig: false,
    skipFormat: true,
    unitTestRunner: "jest",
    linter: "eslint",
  });

  // Add custom files
  const projectConfig = readProjectConfiguration(
    tree,
    `${scope}-feature-${name}`,
  );
  const projectNames = names(name);

  generateFiles(
    tree,
    joinPathFragments(__dirname, "files"),
    projectConfig.sourceRoot,
    {
      ...projectNames,
      scope,
      tmpl: "",
    },
  );

  await formatFiles(tree);
}

Template 5: CI Configuration with Affected

# .github/workflows/ci.yml
name: CI

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

env:
  NX_CLOUD_ACCESS_TOKEN: ${{ secrets.NX_CLOUD_ACCESS_TOKEN }}

jobs:
  main:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - uses: actions/setup-node@v4
        with:
          node-version: 20
          cache: "npm"

      - name: Install dependencies
        run: npm ci

      - name: Derive SHAs for affected commands
        uses: nrwl/nx-set-shas@v4

      - name: Run affected lint
        run: npx nx affected -t lint --parallel=3

      - name: Run affected test
        run: npx nx affected -t test --parallel=3 --configuration=ci

      - name: Run affected build
        run: npx nx affected -t build --parallel=3

      - name: Run affected e2e
        run: npx nx affected -t e2e --parallel=1

Template 6: Remote Caching Setup

// nx.json with Nx Cloud
{
  "tasksRunnerOptions": {
    "default": {
      "runner": "nx-cloud",
      "options": {
        "cacheableOperations": ["build", "lint", "test", "e2e"],
        "accessToken": "your-nx-cloud-token",
        "parallel": 3,
        "cacheDirectory": ".nx/cache"
      }
    }
  },
  "nxCloudAccessToken": "your-nx-cloud-token"
}

// Self-hosted cache with S3
{
  "tasksRunnerOptions": {
    "default": {
      "runner": "@nx-aws-cache/nx-aws-cache",
      "options": {
        "cacheableOperations": ["build", "lint", "test"],
        "awsRegion": "us-east-1",
        "awsBucket": "my-nx-cache-bucket",
        "awsProfile": "default"
      }
    }
  }
}

Common Commands

# Generate new library
nx g @nx/react:lib feature-auth --directory=libs/web --tags=type:feature,scope:web

# Run affected tests
nx affected -t test --base=main

# View dependency graph
nx graph

# Run specific project
nx build web --configuration=production

# Reset cache
nx reset

# Run migrations
nx migrate latest
nx migrate --run-migrations