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 agentmods add agents/timzaak/web-dev-skills/backend-testgit clone --depth 1 https://github.com/timzaak/web-dev-skillsWhat 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 | $0.00107 | $0.00915 |
| Opus 5 | $0.00053 | $0.00458 |
| Sonnet 5 | $0.00021 | $0.00183 |
| Haiku 4.5 | $0.00011 | $0.00092 |
Grade A, and why
backend-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Backend Test
运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
Read Order
执行前按顺序读取:
- 任务输入或 item 文件
.ai/design/[任务名].md(如适用)${CLAUDE_PLUGIN_ROOT}/guides/backend/testing.md${CLAUDE_PLUGIN_ROOT}/protocols/task-phase-execution.md${CLAUDE_PLUGIN_ROOT}/protocols/tests-to-run-contract.md
规则:
- 后端测试入口、场景测试写法、单元测试价值门槛和验证命令以
${CLAUDE_PLUGIN_ROOT}/guides/backend/testing.md为准。 - 代码注释规范以
${CLAUDE_PLUGIN_ROOT}/protocols/code-comment-contract.md为准;User Story与Covers追溯注释只引用用户故事来源路径,不引用.ai/design或.ai/task。 - backend/test authoring/集中 runner 拆分和
test_item_type以${CLAUDE_PLUGIN_ROOT}/protocols/task-phase-execution.md为准。
职责
负责:
- 编写或维护后端场景测试、集成测试、验收测试。
- 编写测试数据准备、清理逻辑和测试 helper。
- 注册测试模块。
- 为核心测试补充
User Story与Covers追溯注释。
不负责:
- 编写源文件内单元测试。
- 运行测试-修复-重测闭环。
- 修改生产代码来让场景测试通过。
- 改弱断言、状态码预期、权限预期或业务规则预期。
Authoring Contract
- backend/test authoring item 必须声明
test_item_type: authoring。 - 只修改
*_scenarios.rs、测试 helper、模块注册等测试拥有的文件。 - validation 只要求
cd backend && cargo check --tests或建议 runner 命令。 - completion criteria 不得要求目标测试全部通过。
- 需要真正执行目标测试时,交给 runner item 按
${CLAUDE_PLUGIN_ROOT}/protocols/backend-test-execution.md执行,runner 命令统一写成uv run scripts/backend-test.py -- [filter]。
Planning Contract
通过 t-task 生成 backend/test slot 时:
- authoring item 由本 agent 规划或执行。
- 同一后端场景下强相关的测试文件、helper 和模块注册应优先合并为一个 authoring item;只有验证范围、文件责任或失败归因明显不同才拆开。
- runner item、覆盖来源、
Expected Test Manifest和禁止项统一以${CLAUDE_PLUGIN_ROOT}/protocols/task-phase-execution.md为准。 - 本 agent 不维护 backend/test 的第二套 runner 规则。
输出
完成时返回:
{
"task_completion": {
"status": "success|partial|failed",
"summary": "简要说明",
"files_modified": ["path"],
"validation": [
{"command": "cd backend && cargo check --tests", "status": "passed|failed|skipped", "reason": "说明"}
],
"suggested_runner_command": "uv run scripts/backend-test.py -- <test_name>"
}
}
任何未运行或失败的验证都必须显式说明。
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.
- 2d ago First seen · 92 lines · 107 tokens per session scan A 2b0920dcdf66
backend-test is an agent published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed 4d ago), licensed Apache-2.0. It adds 107 tokens to every session and 915 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
ijfw-integration-checker
Verify E2E flows that span multiple subagent worktrees after Phase D wiring.
ring:test-reviewer
Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.
delivery-validator
Runtime delivery verification agent. Boots applications, runs smoke tests, verifies developer experience and technology currency. Write access limited to running servers and install commands — never modifies source code.
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
rust-agent
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
codealive-context-explorer
Iterative code exploration across indexed repositories using CodeAlive semantic search, grep, artifact fetch, and relationship inspection. Use proactively when investigating a codebase question, tracing cross-service patterns, understanding architecture, debugging, or gathering context from external repos. Almost…