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

8.0 KiB

name, description
name description
database-migration Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.

Database Migration

Master database schema and data migrations across ORMs (Sequelize, TypeORM, Prisma), including rollback strategies and zero-downtime deployments.

When to Use This Skill

  • Migrating between different ORMs
  • Performing schema transformations
  • Moving data between databases
  • Implementing rollback procedures
  • Zero-downtime deployments
  • Database version upgrades
  • Data model refactoring

ORM Migrations

Sequelize Migrations

// migrations/20231201-create-users.js
module.exports = {
  up: async (queryInterface, Sequelize) => {
    await queryInterface.createTable("users", {
      id: {
        type: Sequelize.INTEGER,
        primaryKey: true,
        autoIncrement: true,
      },
      email: {
        type: Sequelize.STRING,
        unique: true,
        allowNull: false,
      },
      createdAt: Sequelize.DATE,
      updatedAt: Sequelize.DATE,
    });
  },

  down: async (queryInterface, Sequelize) => {
    await queryInterface.dropTable("users");
  },
};

// Run: npx sequelize-cli db:migrate
// Rollback: npx sequelize-cli db:migrate:undo

TypeORM Migrations

// migrations/1701234567-CreateUsers.ts
import { MigrationInterface, QueryRunner, Table } from "typeorm";

export class CreateUsers1701234567 implements MigrationInterface {
  public async up(queryRunner: QueryRunner): Promise<void> {
    await queryRunner.createTable(
      new Table({
        name: "users",
        columns: [
          {
            name: "id",
            type: "int",
            isPrimary: true,
            isGenerated: true,
            generationStrategy: "increment",
          },
          {
            name: "email",
            type: "varchar",
            isUnique: true,
          },
          {
            name: "created_at",
            type: "timestamp",
            default: "CURRENT_TIMESTAMP",
          },
        ],
      }),
    );
  }

  public async down(queryRunner: QueryRunner): Promise<void> {
    await queryRunner.dropTable("users");
  }
}

// Run: npm run typeorm migration:run
// Rollback: npm run typeorm migration:revert

Prisma Migrations

// schema.prisma
model User {
  id        Int      @id @default(autoincrement())
  email     String   @unique
  createdAt DateTime @default(now())
}

// Generate migration: npx prisma migrate dev --name create_users
// Apply: npx prisma migrate deploy

Schema Transformations

Adding Columns with Defaults

// Safe migration: add column with default
module.exports = {
  up: async (queryInterface, Sequelize) => {
    await queryInterface.addColumn("users", "status", {
      type: Sequelize.STRING,
      defaultValue: "active",
      allowNull: false,
    });
  },

  down: async (queryInterface) => {
    await queryInterface.removeColumn("users", "status");
  },
};

Renaming Columns (Zero Downtime)

// Step 1: Add new column
module.exports = {
  up: async (queryInterface, Sequelize) => {
    await queryInterface.addColumn("users", "full_name", {
      type: Sequelize.STRING,
    });

    // Copy data from old column
    await queryInterface.sequelize.query("UPDATE users SET full_name = name");
  },

  down: async (queryInterface) => {
    await queryInterface.removeColumn("users", "full_name");
  },
};

// Step 2: Update application to use new column

// Step 3: Remove old column
module.exports = {
  up: async (queryInterface) => {
    await queryInterface.removeColumn("users", "name");
  },

  down: async (queryInterface, Sequelize) => {
    await queryInterface.addColumn("users", "name", {
      type: Sequelize.STRING,
    });
  },
};

Changing Column Types

module.exports = {
  up: async (queryInterface, Sequelize) => {
    // For large tables, use multi-step approach

    // 1. Add new column
    await queryInterface.addColumn("users", "age_new", {
      type: Sequelize.INTEGER,
    });

    // 2. Copy and transform data
    await queryInterface.sequelize.query(`
      UPDATE users
      SET age_new = CAST(age AS INTEGER)
      WHERE age IS NOT NULL
    `);

    // 3. Drop old column
    await queryInterface.removeColumn("users", "age");

    // 4. Rename new column
    await queryInterface.renameColumn("users", "age_new", "age");
  },

  down: async (queryInterface, Sequelize) => {
    await queryInterface.changeColumn("users", "age", {
      type: Sequelize.STRING,
    });
  },
};

Data Transformations

Complex Data Migration

module.exports = {
  up: async (queryInterface, Sequelize) => {
    // Get all records
    const [users] = await queryInterface.sequelize.query(
      "SELECT id, address_string FROM users",
    );

    // Transform each record
    for (const user of users) {
      const addressParts = user.address_string.split(",");

      await queryInterface.sequelize.query(
        `UPDATE users
         SET street = :street,
             city = :city,
             state = :state
         WHERE id = :id`,
        {
          replacements: {
            id: user.id,
            street: addressParts[0]?.trim(),
            city: addressParts[1]?.trim(),
            state: addressParts[2]?.trim(),
          },
        },
      );
    }

    // Drop old column
    await queryInterface.removeColumn("users", "address_string");
  },

  down: async (queryInterface, Sequelize) => {
    // Reconstruct original column
    await queryInterface.addColumn("users", "address_string", {
      type: Sequelize.STRING,
    });

    await queryInterface.sequelize.query(`
      UPDATE users
      SET address_string = CONCAT(street, ', ', city, ', ', state)
    `);

    await queryInterface.removeColumn("users", "street");
    await queryInterface.removeColumn("users", "city");
    await queryInterface.removeColumn("users", "state");
  },
};

Rollback Strategies

Transaction-Based Migrations

module.exports = {
  up: async (queryInterface, Sequelize) => {
    const transaction = await queryInterface.sequelize.transaction();

    try {
      await queryInterface.addColumn(
        "users",
        "verified",
        { type: Sequelize.BOOLEAN, defaultValue: false },
        { transaction },
      );

      await queryInterface.sequelize.query(
        "UPDATE users SET verified = true WHERE email_verified_at IS NOT NULL",
        { transaction },
      );

      await transaction.commit();
    } catch (error) {
      await transaction.rollback();
      throw error;
    }
  },

  down: async (queryInterface) => {
    await queryInterface.removeColumn("users", "verified");
  },
};

Checkpoint-Based Rollback

module.exports = {
  up: async (queryInterface, Sequelize) => {
    // Create backup table
    await queryInterface.sequelize.query(
      "CREATE TABLE users_backup AS SELECT * FROM users",
    );

    try {
      // Perform migration
      await queryInterface.addColumn("users", "new_field", {
        type: Sequelize.STRING,
      });

      // Verify migration
      const [result] = await queryInterface.sequelize.query(
        "SELECT COUNT(*) as count FROM users WHERE new_field IS NULL",
      );

      if (result[0].count > 0) {
        throw new Error("Migration verification failed");
      }

      // Drop backup
      await queryInterface.dropTable("users_backup");
    } catch (error) {
      // Restore from backup
      await queryInterface.sequelize.query("DROP TABLE users");
      await queryInterface.sequelize.query(
        "CREATE TABLE users AS SELECT * FROM users_backup",
      );
      await queryInterface.dropTable("users_backup");
      throw error;
    }
  },
};

Additional patterns and templates

More detailed templates and worked examples live in references/details.md. Read that file for the full pattern library.