Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Xwen0857/agent-orchestrator --skill tester-ephemeralgit clone --depth 1 https://github.com/Xwen0857/agent-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xwen0857/agent-orchestrator/tester-ephemeral)<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/tester-ephemeral"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/tester-ephemeral/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/tester-ephemeral"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/tester-ephemeral.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.02369 |
| Opus 5 | $0.00015 | $0.01184 |
| Sonnet 5 | $0.00006 | $0.00474 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
tester-ephemeral scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tester Ephemeral
V2 基线（强制优先）
- tester-ephemeral 必须从
templates/coordination/tasks/task_folders/<task_id>/meta.json读取任务上下文，且仅在TESTING状态执行验收。 - 验收结果仅允许推进为
APPROVED或REJECTED，并强制追加事件到log.ndjson。 result.md/result.json必须回链task_id与operation_id，确保可审计与幂等重放。- 若验证过程命中高风险测试动作，必须先交由 audit-guard 决策后再继续。
核心职责
- 根据 worker 交接任务执行一次性测试，不参与长期状态维护。
- 输出标准化测试结果，供 planner 与 worker 进行验收或修复决策。
- 对失败项提供可执行修复建议，缩短反馈闭环。
- 结果回传后立即终止 tester 实例，避免状态污染。
输入文件相对路径
- 测试任务文件路径：
templates/coordination/testers/<run_id>/task.md。 - worker 任务运行文件路径（新）：
$AGENT_ORCHESTRATOR_STATE_DIR/tasks/worker_tasks/<worker_id>_tasks.md（默认~/.openclaw-state/agent-orchestrator/tasks/worker_tasks/<worker_id>_tasks.md）。 - worker 任务文件路径（兼容）：
templates/coordination/tasks/<worker_id>_tasks.md。 - worker 状态文件路径：
templates/coordination/workers/<worker_id>_worker.md。 - 执行接口定义路径：项目根目录
interface.json。 - planner 生效配置路径：
templates/coordination/planner/config/current.md。
输出文件相对路径
- 测试结果文件路径：
templates/coordination/testers/<run_id>/result.md。 - 测试结果结构化文件路径：
templates/coordination/testers/<run_id>/result.json。 - tester 日志摘要路径：
templates/coordination/testers/tester_logs/<worker_id>_test_logs.md。 - worker 任务回写运行路径（新）：
$AGENT_ORCHESTRATOR_STATE_DIR/tasks/worker_tasks/<worker_id>_tasks.md。 - worker 任务兼容镜像路径（只读）：
templates/coordination/tasks/<worker_id>_tasks.md。
读取文件相对路径
- 读取
templates/coordination/testers/<run_id>/task.md获取测试范围、命令和通过标准。 - 优先读取运行态
worker_tasks/<worker_id>_tasks.md（默认~/.openclaw-state/agent-orchestrator/tasks/worker_tasks/<worker_id>_tasks.md）获取当前任务状态与尝试次数。 - 若新路径文件不存在，则回退读取
templates/coordination/tasks/<worker_id>_tasks.md。 - 读取
templates/coordination/workers/<worker_id>_worker.md获取 worker 上下文。 - 读取
interface.json获取接口或契约约束。 - 读取
templates/coordination/planner/config/current.md获取当前编排测试策略。
生命周期流程
- 接收
run_id与 worker 交接任务，初始化一次性 tester。 - 按
task.md中commands和pass_criteria执行测试。 - 生成
result.md与result.json，写入状态、失败码、证据与修复建议。 - 若本次交接来源于 mailbox + wrapper export，tester 仅消费 exported artifact reference，并在消费/归档后更新
delivery.export-records.json的 lifecycle 状态。 - 回写 worker 任务状态（PASS/FAIL）并记录 tester 日志摘要。
- 将结果回传 orchestrator/planner 后终止 tester。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 149 lines · 30 tokens per session scan A 2eb91fb5ad67
tester-ephemeral is a skill published in the GitHub repository Xwen0857/agent-orchestrator (2 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 2,369 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
testing-and-ci
Testing conventions, CI pipeline rules, and smoke test coverage for SkillHub. Ensures agents write tests correctly and understand the CI gate requirements.
qa
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…
qa-only
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively…
plan
A planning skill that turns a spec.md specification into a milestone-based implementation plan using test-driven development (TDD), where tests are written to guide the code.
execute
A milestone-based coding workflow that uses test-driven development (TDD): write a test, implement the change, and verify it for each milestone listed in milestones.json.