wshobson--agents
be57c0b2e3
* 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
314 行
7.0 KiB
Markdown
314 行
7.0 KiB
Markdown
---
|
|
name: angular-migration
|
|
description: Migrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and dependency injection updates. Use when upgrading AngularJS applications, planning framework migrations, or modernizing legacy Angular code.
|
|
---
|
|
|
|
# Angular Migration
|
|
|
|
Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing migration.
|
|
|
|
## When to Use This Skill
|
|
|
|
- Migrating AngularJS (1.x) applications to Angular (2+)
|
|
- Running hybrid AngularJS/Angular applications
|
|
- Converting directives to components
|
|
- Modernizing dependency injection
|
|
- Migrating routing systems
|
|
- Updating to latest Angular versions
|
|
- Implementing Angular best practices
|
|
|
|
## Migration Strategies
|
|
|
|
### 1. Big Bang (Complete Rewrite)
|
|
|
|
- Rewrite entire app in Angular
|
|
- Parallel development
|
|
- Switch over at once
|
|
- **Best for:** Small apps, green field projects
|
|
|
|
### 2. Incremental (Hybrid Approach)
|
|
|
|
- Run AngularJS and Angular side-by-side
|
|
- Migrate feature by feature
|
|
- ngUpgrade for interop
|
|
- **Best for:** Large apps, continuous delivery
|
|
|
|
### 3. Vertical Slice
|
|
|
|
- Migrate one feature completely
|
|
- New features in Angular, maintain old in AngularJS
|
|
- Gradually replace
|
|
- **Best for:** Medium apps, distinct features
|
|
|
|
## Hybrid App Setup
|
|
|
|
```typescript
|
|
// main.ts - Bootstrap hybrid app
|
|
import { platformBrowserDynamic } from "@angular/platform-browser-dynamic";
|
|
import { UpgradeModule } from "@angular/upgrade/static";
|
|
import { AppModule } from "./app/app.module";
|
|
|
|
platformBrowserDynamic()
|
|
.bootstrapModule(AppModule)
|
|
.then((platformRef) => {
|
|
const upgrade = platformRef.injector.get(UpgradeModule);
|
|
// Bootstrap AngularJS
|
|
upgrade.bootstrap(document.body, ["myAngularJSApp"], { strictDi: true });
|
|
});
|
|
```
|
|
|
|
```typescript
|
|
// app.module.ts
|
|
import { NgModule } from "@angular/core";
|
|
import { BrowserModule } from "@angular/platform-browser";
|
|
import { UpgradeModule } from "@angular/upgrade/static";
|
|
|
|
@NgModule({
|
|
imports: [BrowserModule, UpgradeModule],
|
|
})
|
|
export class AppModule {
|
|
constructor(private upgrade: UpgradeModule) {}
|
|
|
|
ngDoBootstrap() {
|
|
// Bootstrapped manually in main.ts
|
|
}
|
|
}
|
|
```
|
|
|
|
## Component Migration
|
|
|
|
### AngularJS Controller → Angular Component
|
|
|
|
```javascript
|
|
// Before: AngularJS controller
|
|
angular
|
|
.module("myApp")
|
|
.controller("UserController", function ($scope, UserService) {
|
|
$scope.user = {};
|
|
|
|
$scope.loadUser = function (id) {
|
|
UserService.getUser(id).then(function (user) {
|
|
$scope.user = user;
|
|
});
|
|
};
|
|
|
|
$scope.saveUser = function () {
|
|
UserService.saveUser($scope.user);
|
|
};
|
|
});
|
|
```
|
|
|
|
```typescript
|
|
// After: Angular component
|
|
import { Component, OnInit } from "@angular/core";
|
|
import { UserService } from "./user.service";
|
|
|
|
@Component({
|
|
selector: "app-user",
|
|
template: `
|
|
<div>
|
|
<h2>{{ user.name }}</h2>
|
|
<button (click)="saveUser()">Save</button>
|
|
</div>
|
|
`,
|
|
})
|
|
export class UserComponent implements OnInit {
|
|
user: any = {};
|
|
|
|
constructor(private userService: UserService) {}
|
|
|
|
ngOnInit() {
|
|
this.loadUser(1);
|
|
}
|
|
|
|
loadUser(id: number) {
|
|
this.userService.getUser(id).subscribe((user) => {
|
|
this.user = user;
|
|
});
|
|
}
|
|
|
|
saveUser() {
|
|
this.userService.saveUser(this.user);
|
|
}
|
|
}
|
|
```
|
|
|
|
### AngularJS Directive → Angular Component
|
|
|
|
```javascript
|
|
// Before: AngularJS directive
|
|
angular.module("myApp").directive("userCard", function () {
|
|
return {
|
|
restrict: "E",
|
|
scope: {
|
|
user: "=",
|
|
onDelete: "&",
|
|
},
|
|
template: `
|
|
<div class="card">
|
|
<h3>{{ user.name }}</h3>
|
|
<button ng-click="onDelete()">Delete</button>
|
|
</div>
|
|
`,
|
|
};
|
|
});
|
|
```
|
|
|
|
```typescript
|
|
// After: Angular component
|
|
import { Component, Input, Output, EventEmitter } from "@angular/core";
|
|
|
|
@Component({
|
|
selector: "app-user-card",
|
|
template: `
|
|
<div class="card">
|
|
<h3>{{ user.name }}</h3>
|
|
<button (click)="delete.emit()">Delete</button>
|
|
</div>
|
|
`,
|
|
})
|
|
export class UserCardComponent {
|
|
@Input() user: any;
|
|
@Output() delete = new EventEmitter<void>();
|
|
}
|
|
|
|
// Usage: <app-user-card [user]="user" (delete)="handleDelete()"></app-user-card>
|
|
```
|
|
|
|
## Service Migration
|
|
|
|
```javascript
|
|
// Before: AngularJS service
|
|
angular.module("myApp").factory("UserService", function ($http) {
|
|
return {
|
|
getUser: function (id) {
|
|
return $http.get("/api/users/" + id);
|
|
},
|
|
saveUser: function (user) {
|
|
return $http.post("/api/users", user);
|
|
},
|
|
};
|
|
});
|
|
```
|
|
|
|
```typescript
|
|
// After: Angular service
|
|
import { Injectable } from "@angular/core";
|
|
import { HttpClient } from "@angular/common/http";
|
|
import { Observable } from "rxjs";
|
|
|
|
@Injectable({
|
|
providedIn: "root",
|
|
})
|
|
export class UserService {
|
|
constructor(private http: HttpClient) {}
|
|
|
|
getUser(id: number): Observable<any> {
|
|
return this.http.get(`/api/users/${id}`);
|
|
}
|
|
|
|
saveUser(user: any): Observable<any> {
|
|
return this.http.post("/api/users", user);
|
|
}
|
|
}
|
|
```
|
|
|
|
## Dependency Injection Changes
|
|
|
|
### Downgrading Angular → AngularJS
|
|
|
|
```typescript
|
|
// Angular service
|
|
import { Injectable } from "@angular/core";
|
|
|
|
@Injectable({ providedIn: "root" })
|
|
export class NewService {
|
|
getData() {
|
|
return "data from Angular";
|
|
}
|
|
}
|
|
|
|
// Make available to AngularJS
|
|
import { downgradeInjectable } from "@angular/upgrade/static";
|
|
|
|
angular.module("myApp").factory("newService", downgradeInjectable(NewService));
|
|
|
|
// Use in AngularJS
|
|
angular.module("myApp").controller("OldController", function (newService) {
|
|
console.log(newService.getData());
|
|
});
|
|
```
|
|
|
|
### Upgrading AngularJS → Angular
|
|
|
|
```typescript
|
|
// AngularJS service
|
|
angular.module('myApp').factory('oldService', function() {
|
|
return {
|
|
getData: function() {
|
|
return 'data from AngularJS';
|
|
}
|
|
};
|
|
});
|
|
|
|
// Make available to Angular
|
|
import { InjectionToken } from '@angular/core';
|
|
|
|
export const OLD_SERVICE = new InjectionToken<any>('oldService');
|
|
|
|
@NgModule({
|
|
providers: [
|
|
{
|
|
provide: OLD_SERVICE,
|
|
useFactory: (i: any) => i.get('oldService'),
|
|
deps: ['$injector']
|
|
}
|
|
]
|
|
})
|
|
|
|
// Use in Angular
|
|
@Component({...})
|
|
export class NewComponent {
|
|
constructor(@Inject(OLD_SERVICE) private oldService: any) {
|
|
console.log(this.oldService.getData());
|
|
}
|
|
}
|
|
```
|
|
|
|
## Routing Migration
|
|
|
|
```javascript
|
|
// Before: AngularJS routing
|
|
angular.module("myApp").config(function ($routeProvider) {
|
|
$routeProvider
|
|
.when("/users", {
|
|
template: "<user-list></user-list>",
|
|
})
|
|
.when("/users/:id", {
|
|
template: "<user-detail></user-detail>",
|
|
});
|
|
});
|
|
```
|
|
|
|
```typescript
|
|
// After: Angular routing
|
|
import { NgModule } from "@angular/core";
|
|
import { RouterModule, Routes } from "@angular/router";
|
|
|
|
const routes: Routes = [
|
|
{ path: "users", component: UserListComponent },
|
|
{ path: "users/:id", component: UserDetailComponent },
|
|
];
|
|
|
|
@NgModule({
|
|
imports: [RouterModule.forRoot(routes)],
|
|
exports: [RouterModule],
|
|
})
|
|
export class AppRoutingModule {}
|
|
```
|
|
|
|
## Additional patterns and templates
|
|
|
|
More detailed templates and worked examples live in `references/details.md`. Read that file for the full pattern library.
|
|
|