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
10 KiB
10 KiB
e2e-testing-patterns — detailed patterns and worked examples
Playwright Patterns
Setup and Configuration
// playwright.config.ts
import { defineConfig, devices } from "@playwright/test";
export default defineConfig({
testDir: "./e2e",
timeout: 30000,
expect: {
timeout: 5000,
},
fullyParallel: true,
forbidOnly: !!process.env.CI,
retries: process.env.CI ? 2 : 0,
workers: process.env.CI ? 1 : undefined,
reporter: [["html"], ["junit", { outputFile: "results.xml" }]],
use: {
baseURL: "http://localhost:3000",
trace: "on-first-retry",
screenshot: "only-on-failure",
video: "retain-on-failure",
},
projects: [
{ name: "chromium", use: { ...devices["Desktop Chrome"] } },
{ name: "firefox", use: { ...devices["Desktop Firefox"] } },
{ name: "webkit", use: { ...devices["Desktop Safari"] } },
{ name: "mobile", use: { ...devices["iPhone 13"] } },
],
});
Pattern 1: Page Object Model
// pages/LoginPage.ts
import { Page, Locator } from "@playwright/test";
export class LoginPage {
readonly page: Page;
readonly emailInput: Locator;
readonly passwordInput: Locator;
readonly loginButton: Locator;
readonly errorMessage: Locator;
constructor(page: Page) {
this.page = page;
this.emailInput = page.getByLabel("Email");
this.passwordInput = page.getByLabel("Password");
this.loginButton = page.getByRole("button", { name: "Login" });
this.errorMessage = page.getByRole("alert");
}
async goto() {
await this.page.goto("/login");
}
async login(email: string, password: string) {
await this.emailInput.fill(email);
await this.passwordInput.fill(password);
await this.loginButton.click();
}
async getErrorMessage(): Promise<string> {
return (await this.errorMessage.textContent()) ?? "";
}
}
// Test using Page Object
import { test, expect } from "@playwright/test";
import { LoginPage } from "./pages/LoginPage";
test("successful login", async ({ page }) => {
const loginPage = new LoginPage(page);
await loginPage.goto();
await loginPage.login("user@example.com", "password123");
await expect(page).toHaveURL("/dashboard");
await expect(page.getByRole("heading", { name: "Dashboard" })).toBeVisible();
});
test("failed login shows error", async ({ page }) => {
const loginPage = new LoginPage(page);
await loginPage.goto();
await loginPage.login("invalid@example.com", "wrong");
const error = await loginPage.getErrorMessage();
expect(error).toContain("Invalid credentials");
});
Pattern 2: Fixtures for Test Data
// fixtures/test-data.ts
import { test as base } from "@playwright/test";
type TestData = {
testUser: {
email: string;
password: string;
name: string;
};
adminUser: {
email: string;
password: string;
};
};
export const test = base.extend<TestData>({
testUser: async ({}, use) => {
const user = {
email: `test-${Date.now()}@example.com`,
password: "Test123!@#",
name: "Test User",
};
// Setup: Create user in database
await createTestUser(user);
await use(user);
// Teardown: Clean up user
await deleteTestUser(user.email);
},
adminUser: async ({}, use) => {
await use({
email: "admin@example.com",
password: process.env.ADMIN_PASSWORD!,
});
},
});
// Usage in tests
import { test } from "./fixtures/test-data";
test("user can update profile", async ({ page, testUser }) => {
await page.goto("/login");
await page.getByLabel("Email").fill(testUser.email);
await page.getByLabel("Password").fill(testUser.password);
await page.getByRole("button", { name: "Login" }).click();
await page.goto("/profile");
await page.getByLabel("Name").fill("Updated Name");
await page.getByRole("button", { name: "Save" }).click();
await expect(page.getByText("Profile updated")).toBeVisible();
});
Pattern 3: Waiting Strategies
// ❌ Bad: Fixed timeouts
await page.waitForTimeout(3000); // Flaky!
// ✅ Good: Wait for specific conditions
await page.waitForLoadState("networkidle");
await page.waitForURL("/dashboard");
await page.waitForSelector('[data-testid="user-profile"]');
// ✅ Better: Auto-waiting with assertions
await expect(page.getByText("Welcome")).toBeVisible();
await expect(page.getByRole("button", { name: "Submit" })).toBeEnabled();
// Wait for API response
const responsePromise = page.waitForResponse(
(response) =>
response.url().includes("/api/users") && response.status() === 200,
);
await page.getByRole("button", { name: "Load Users" }).click();
const response = await responsePromise;
const data = await response.json();
expect(data.users).toHaveLength(10);
// Wait for multiple conditions
await Promise.all([
page.waitForURL("/success"),
page.waitForLoadState("networkidle"),
expect(page.getByText("Payment successful")).toBeVisible(),
]);
Pattern 4: Network Mocking and Interception
// Mock API responses
test("displays error when API fails", async ({ page }) => {
await page.route("**/api/users", (route) => {
route.fulfill({
status: 500,
contentType: "application/json",
body: JSON.stringify({ error: "Internal Server Error" }),
});
});
await page.goto("/users");
await expect(page.getByText("Failed to load users")).toBeVisible();
});
// Intercept and modify requests
test("can modify API request", async ({ page }) => {
await page.route("**/api/users", async (route) => {
const request = route.request();
const postData = JSON.parse(request.postData() || "{}");
// Modify request
postData.role = "admin";
await route.continue({
postData: JSON.stringify(postData),
});
});
// Test continues...
});
// Mock third-party services
test("payment flow with mocked Stripe", async ({ page }) => {
await page.route("**/api/stripe/**", (route) => {
route.fulfill({
status: 200,
body: JSON.stringify({
id: "mock_payment_id",
status: "succeeded",
}),
});
});
// Test payment flow with mocked response
});
Cypress Patterns
Setup and Configuration
// cypress.config.ts
import { defineConfig } from "cypress";
export default defineConfig({
e2e: {
baseUrl: "http://localhost:3000",
viewportWidth: 1280,
viewportHeight: 720,
video: false,
screenshotOnRunFailure: true,
defaultCommandTimeout: 10000,
requestTimeout: 10000,
setupNodeEvents(on, config) {
// Implement node event listeners
},
},
});
Pattern 1: Custom Commands
// cypress/support/commands.ts
declare global {
namespace Cypress {
interface Chainable {
login(email: string, password: string): Chainable<void>;
createUser(userData: UserData): Chainable<User>;
dataCy(value: string): Chainable<JQuery<HTMLElement>>;
}
}
}
Cypress.Commands.add("login", (email: string, password: string) => {
cy.visit("/login");
cy.get('[data-testid="email"]').type(email);
cy.get('[data-testid="password"]').type(password);
cy.get('[data-testid="login-button"]').click();
cy.url().should("include", "/dashboard");
});
Cypress.Commands.add("createUser", (userData: UserData) => {
return cy.request("POST", "/api/users", userData).its("body");
});
Cypress.Commands.add("dataCy", (value: string) => {
return cy.get(`[data-cy="${value}"]`);
});
// Usage
cy.login("user@example.com", "password");
cy.dataCy("submit-button").click();
Pattern 2: Cypress Intercept
// Mock API calls
cy.intercept("GET", "/api/users", {
statusCode: 200,
body: [
{ id: 1, name: "John" },
{ id: 2, name: "Jane" },
],
}).as("getUsers");
cy.visit("/users");
cy.wait("@getUsers");
cy.get('[data-testid="user-list"]').children().should("have.length", 2);
// Modify responses
cy.intercept("GET", "/api/users", (req) => {
req.reply((res) => {
// Modify response
res.body.users = res.body.users.slice(0, 5);
res.send();
});
});
// Simulate slow network
cy.intercept("GET", "/api/data", (req) => {
req.reply((res) => {
res.delay(3000); // 3 second delay
res.send();
});
});
Advanced Patterns
Pattern 1: Visual Regression Testing
// With Playwright
import { test, expect } from "@playwright/test";
test("homepage looks correct", async ({ page }) => {
await page.goto("/");
await expect(page).toHaveScreenshot("homepage.png", {
fullPage: true,
maxDiffPixels: 100,
});
});
test("button in all states", async ({ page }) => {
await page.goto("/components");
const button = page.getByRole("button", { name: "Submit" });
// Default state
await expect(button).toHaveScreenshot("button-default.png");
// Hover state
await button.hover();
await expect(button).toHaveScreenshot("button-hover.png");
// Disabled state
await button.evaluate((el) => el.setAttribute("disabled", "true"));
await expect(button).toHaveScreenshot("button-disabled.png");
});
Pattern 2: Parallel Testing with Sharding
// playwright.config.ts
export default defineConfig({
projects: [
{
name: "shard-1",
use: { ...devices["Desktop Chrome"] },
grepInvert: /@slow/,
shard: { current: 1, total: 4 },
},
{
name: "shard-2",
use: { ...devices["Desktop Chrome"] },
shard: { current: 2, total: 4 },
},
// ... more shards
],
});
// Run in CI
// npx playwright test --shard=1/4
// npx playwright test --shard=2/4
Pattern 3: Accessibility Testing
// Install: npm install @axe-core/playwright
import { test, expect } from "@playwright/test";
import AxeBuilder from "@axe-core/playwright";
test("page should not have accessibility violations", async ({ page }) => {
await page.goto("/");
const accessibilityScanResults = await new AxeBuilder({ page })
.exclude("#third-party-widget")
.analyze();
expect(accessibilityScanResults.violations).toEqual([]);
});
test("form is accessible", async ({ page }) => {
await page.goto("/signup");
const results = await new AxeBuilder({ page }).include("form").analyze();
expect(results.violations).toEqual([]);
});