test-matrix
Use for browser-rendered Web behavior and Web-side API journeys.
$ npx -y skills add AgentsMesh/AgentsMesh --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Use for browser-rendered Web behavior and Web-side API journeys.
Agent definition
test-matrix.mdAgentsMesh E2E Test Matrix
Web
Use for browser-rendered Web behavior and Web-side API journeys.
bazel run //deploy/dev:up
set -a
source deploy/dev/.env
set +a
E2E_OUTPUT_BASE="${TMPDIR:-/tmp}/bazel-${COMPOSE_PROJECT_NAME}-web-e2e"
bazel --output_base="$E2E_OUTPUT_BASE" test \
//clients/web/e2e-playwright:e2e \
--test_tag_filters=e2e \
--test_output=errors \
--test_env=HTTP_PORT \
--test_env=WEB_PORT \
--test_env=POSTGRES_PORT \
--test_env=COMPOSE_PROJECT_NAMEPass a Playwright spec or title pattern after the target flags for a narrow run:
--test_arg=tests/auth/login.spec.ts
--test_arg=--grep=<title-pattern>
Tests live under `clients/web/e2e-playwright/tests/`. Shared connection, environment, database, and browser helpers live alongside them in `helpers/`, `fixtures/`, and `pages/`. Install the browser once with `pnpm exec playwright install chromium` if Playwright reports a missing executable.
Desktop
Use for Electron main/preload/renderer integration, IPC contracts, persistence, popout windows, or behavior that differs from the Web browser.
bazel run //deploy/dev:backend_only
set -a
source deploy/dev/.env
set +a
E2E_OUTPUT_BASE="${TMPDIR:-/tmp}/bazel-${COMPOSE_PROJECT_NAME}-desktop-e2e"
bazel --output_base="$E2E_OUTPUT_BASE" test \
//clients/desktop:e2e \
--test_tag_filters=e2e \
--test_output=errors \
--test_env=HTTP_PORT \
--test_env=POSTGRES_PORT \
--test_env=COMPOSE_PROJECT_NAMEDesktop specs live under `clients/desktop/e2e/tests/`. Pass a spec path with `--test_arg` for a narrow run. Electron E2E requires a host capable of launching the desktop application.
MCP
Use for the Runner MCP HTTP server and the full Runner to Backend to database chain.
bazel run //deploy/dev:backend_only
set -a
source deploy/dev/.env
set +a
export MCP_PORT="$RUNNER_MCP_PORT"
export POSTGRES_USER=agentsmesh
export POSTGRES_DB=agentsmesh
E2E_OUTPUT_BASE="${TMPDIR:-/tmp}/bazel-${COMPOSE_PROJECT_NAME}-mcp-e2e"
bazel --output_base="$E2E_OUTPUT_BASE" test \
//tests/mcp-e2e/suites:e2e \
--test_tag_filters=e2e \
--test_output=errors \
--test_env=MCP_PORT \
--test_env=RUNNER_2_MCP_PORT \
--test_env=BACKEND_HTTP_PORT \
--test_env=POSTGRES_PORT \
--test_env=POSTGRES_USER \
--test_env=POSTGRES_PASSWORD \
--test_env=POSTGRES_DBUse `--test_filter` for a narrow Go test. Treat `.github/workflows/bazel.yml` as the authoritative environment contract when older prose disagrees with CI.
The dedicated output bases keep each test command from tearing down the Bazel processes that serve the running development stack.
iOS
Use for SwiftUI navigation, native rendering, and iOS-specific integration on a macOS host with Xcode and a booted simulator:
bazel test //clients/ios/Tests/AgentsMeshUITests:AgentsMesh_e2e
Specs live under `clients/ios/Tests/AgentsMeshUITests/Specs/`. Read `Helpers/Env.swift` before overriding the development API endpoint.
Failure Evidence
deploy/dev/runtime/backend/backend.log
deploy/dev/runtime/relay/relay.log
deploy/dev/runtime/runner/runner.log
deploy/dev/web.log
test-results/
clients/web/e2e-playwright/playwright-report/
clients/desktop/playwright-report/
Read more
AgentsMesh E2E Test Matrix
Web
Use for browser-rendered Web behavior and Web-side API journeys.
bazel run //deploy/dev:up
set -a
source deploy/dev/.env
set +a
E2E_OUTPUT_BASE="${TMPDIR:-/tmp}/bazel-${COMPOSE_PROJECT_NAME}-web-e2e"
bazel --output_base="$E2E_OUTPUT_BASE" test \
//clients/web/e2e-playwright:e2e \
--test_tag_filters=e2e \
--test_output=errors \
--test_env=HTTP_PORT \
--test_env=WEB_PORT \
--test_env=POSTGRES_PORT \
--test_env=COMPOSE_PROJECT_NAMEPass a Playwright spec or title pattern after the target flags for a narrow run:
--test_arg=tests/auth/login.spec.ts --test_arg=--grep=<title-pattern>
Tests live under `clients/web/e2e-playwright/tests/`. Shared connection, environment, database, and browser helpers live alongside them in `helpers/`, `fixtures/`, and `pages/`. Install the browser once with `pnpm exec playwright install chromium` if Playwright reports a missing executable.
Desktop
Use for Electron main/preload/renderer integration, IPC contracts, persistence, popout windows, or behavior that differs from the Web browser.
bazel run //deploy/dev:backend_only
set -a
source deploy/dev/.env
set +a
E2E_OUTPUT_BASE="${TMPDIR:-/tmp}/bazel-${COMPOSE_PROJECT_NAME}-desktop-e2e"
bazel --output_base="$E2E_OUTPUT_BASE" test \
//clients/desktop:e2e \
--test_tag_filters=e2e \
--test_output=errors \
--test_env=HTTP_PORT \
--test_env=POSTGRES_PORT \
--test_env=COMPOSE_PROJECT_NAMEDesktop specs live under `clients/desktop/e2e/tests/`. Pass a spec path with `--test_arg` for a narrow run. Electron E2E requires a host capable of launching the desktop application.
MCP
Use for the Runner MCP HTTP server and the full Runner to Backend to database chain.
bazel run //deploy/dev:backend_only
set -a
source deploy/dev/.env
set +a
export MCP_PORT="$RUNNER_MCP_PORT"
export POSTGRES_USER=agentsmesh
export POSTGRES_DB=agentsmesh
E2E_OUTPUT_BASE="${TMPDIR:-/tmp}/bazel-${COMPOSE_PROJECT_NAME}-mcp-e2e"
bazel --output_base="$E2E_OUTPUT_BASE" test \
//tests/mcp-e2e/suites:e2e \
--test_tag_filters=e2e \
--test_output=errors \
--test_env=MCP_PORT \
--test_env=RUNNER_2_MCP_PORT \
--test_env=BACKEND_HTTP_PORT \
--test_env=POSTGRES_PORT \
--test_env=POSTGRES_USER \
--test_env=POSTGRES_PASSWORD \
--test_env=POSTGRES_DBUse `--test_filter` for a narrow Go test. Treat `.github/workflows/bazel.yml` as the authoritative environment contract when older prose disagrees with CI.
The dedicated output bases keep each test command from tearing down the Bazel processes that serve the running development stack.
iOS
Use for SwiftUI navigation, native rendering, and iOS-specific integration on a macOS host with Xcode and a booted simulator:
bazel test //clients/ios/Tests/AgentsMeshUITests:AgentsMesh_e2e
Specs live under `clients/ios/Tests/AgentsMeshUITests/Specs/`. Read `Helpers/Env.swift` before overriding the development API endpoint.
Failure Evidence
deploy/dev/runtime/backend/backend.log deploy/dev/runtime/relay/relay.log deploy/dev/runtime/runner/runner.log deploy/dev/web.log test-results/ clients/web/e2e-playwright/playwright-report/ clients/desktop/playwright-report/
The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.
Repo: AgentsMesh/AgentsMesh
Other agents on agentsmesh.
- cochange-churn
静态切面看不到的架构问题,往往在**版本历史**里暴露。这是来自代码审查 git-history lens 的高信号视角。仅当处于 git 仓库时启用。
Open agent - concept-modeling
架构的本质是**概念的识别与组织**。这是优先级最高的 lens。
Open agent - evidence-and-detection
LLM 架构审查的头号失败模式:**凭空断言结构**——声称"A 依赖 B""这里有循环""X 被多处写",却没真去查。本文件给出强制接地原则 + 各语言的实际探测命令。
Open agent - report-format
范围小用 SKILL.md 里的精简版即可。下面是全量审计的结构化报告。
Open agent - responsibility-causality
这是本 skill 最独特、最能抓**真实结构性 bug** 的 lens:职责归属、机制/策略分离、因果与不变量(并发/状态契约)、属性三分。
Open agent - solid-grasp-yagni
经典原则做交叉验证。**这一 lens 最容易产出假阳性(教科书式建议)——严格用置信度门控,不报"理论上更优雅但无实际危害"的项。**
Open agent

