Borrowing it
Nothing to install: this file belongs to fitlab-ai/agent-infra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fitlab-ai/agent-infra/main/.agents/skills/run-manual-validation/SKILL.mdgit clone --depth 1 https://github.com/fitlab-ai/agent-infraWrote 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/fitlab-ai/agent-infra/run-manual-validation)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/run-manual-validation"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/run-manual-validation/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/fitlab-ai/agent-infra/run-manual-validation"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/run-manual-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01952 |
| Opus 5.5 | $0.00024 | $0.00781 |
| Sonnet 5.5 | $0.00012 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
run-manual-validation 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 today.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
运行人工校验
生命周期事件必须携带显式触发信息：普通技能调用使用 model；仅用户明确要求时使用 human。{request-id} 是本任务与本轮产物的稳定单行标识，{reason-code} 使用 user-request 或 validation-rerun；started 与 completed 使用同一组值。
任务上下文解析
入口可省略 task ref；显式 task scope 仅接受 --task <ref> 或 -t <ref>，不再解释位置 task ref。先解析 --scope、--timeout、--format，在 -- 后原样保留用户命令，再调用 agent-infra-internal task-context resolve {task-scope}。解析失败时透传非零退出码，不自行扫描任务。内部 task-validate 协议仍使用位置 task ref。
跨环境校验（任务工作区在另一台宿主）显式传 --branch <ref> 进入 branch-only 降级路径：不调用 task-context resolve，直接以该分支 ref 作为 task-validate 的位置参数，核心据此返回 taskId: null 的 branch-only 证据。未传 --branch 时解析失败仍透传非零退出码，不得静默降级。--task 与 --branch 互斥。
行为边界
持久化报告证据
生成验证报告时，先读取 .agents/rules/evidence-reporting.md。只记录命令名称、目标范围、退出状态、sanitized result 和覆盖缺口；不得记录完整 argv、环境变量、token、绝对路径或原始敏感 transcript。
- 本技能负责选择校验模式、调用唯一机械入口并记录证据；不把 PR 人工校验标为完成。
complete-manual-validation仍是维护者确认覆盖充分后的最终登记入口。- 禁止直接操作临时 worktree、lease 或 container；只调用
agent-infra-internal task-validate。 - 产物不得记录 token、环境变量、完整 argv、绝对用户路径或原始 transcript；每个验证目标必须由核心写入同一 current-only evidence envelope。
- 生成会由 task 评论引用的验证 artifact Markdown 前，先读取
.agents/rules/sync-content-generation.md并遵循其中的生成端约束；验证 artifact 保留在本地，不发布为 Issue artifact 评论。 - branch-only 降级路径在系统临时目录下创建一次
tmp-开头的独立目录，标记recoverable: false：不写 task.md、不发 lifecycle 事件、不同步 Issue、不跑task-verify；报告与 evidence 同目录，结果提供取回路径，产物须带回宿主机由维护者登记。
第 0 步：状态核对（执行前硬约束）
解析任务引用后运行，并在产物中记录任务/产物范围、关键结果和未覆盖部分；正常成功不粘贴完整目录清单或 task.md 尾部，失败、阻塞、身份不一致或争议时附决定性原文行：
agent-infra-internal task-snapshot {task-id} --format text
branch-only 无 {task-id}，跳过本步，并在产物 ## 状态核对 记录 not-applicable (branch-only)。
执行步骤
- 读取
reference/discovery-and-execution.md，解析输入模式；非法或半截输入在 started 前停止，不写产物。 - 运行
agent-infra-internal task-artifact {task-id} inspect --family validation-run，读取最新 review-code 人工校验项；再运行agent-infra-internal platform-pr inspect {task-id}，按 reference 的状态矩阵发现、归并并编号。仅在自动模式下，可靠来源无项或唯一可能来源不可读时才在 started 前停止；合法显式模式始终以用户命令作为有效工作继续。 - 从核心结果取得轮次和产物名；确认存在有效显式工作或非空发现清单后，运行
agent-infra-internal task-event {task-id} validation-run.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}，并逐项分类为executable|unavailable|unknown|unsafe|unresolved。 - 按
reference/discovery-and-execution.md为本轮选择一次产物目录，并为每个验证目标和执行 scope 分配唯一{evidence-file}；将路径作为一个引用参数传给现有--evidence-file。分别调用agent-infra-internal task-validate {task-ref} --scope snapshot --format json --evidence-file {evidence-file} -- {command...}；只有证据表明必须原位时才对该项进行第二次显式 inplace 调用。零项可执行时不运行伪造命令，但仍继续产出覆盖缺口证据。 - 读取
reference/report-template.md，创建validation-run.md|validation-run-r{N}.md；记录输入模式、发现清单、逐项结果、CLI JSON allowlist 与去敏摘要。 - 运行
agent-infra-internal task-event {task-id} validation-run.completed --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code} --artifact {artifact}。存在 Issue 时仅运行agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}；验证 artifact 不发布为 Issue 评论。 - 运行
agent-infra-internal task-verify {task-id} validation-run.completed --artifact {artifact} --format text；未通过则修复后重跑，并按.agents/rules/validation-output.md展示摘要和必要诊断。 - 告知用户证据路径、覆盖缺口和验证结果；明确仍需维护者判断是否执行
complete-manual-validation。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed d09d0a216d8a
- 11d ago Changed b468154d340b
- 23d ago Changed b12d690ea0a4
- 1mo ago Changed 6136bf57ff4d
- 1mo ago Changed 66ab1157437d
- 1mo ago Changed · +17 lines d19a2248e045
- 1mo ago Changed · +4 lines 2d67d49b4998
- 1mo ago Changed · +2 lines a69e129adc4e
- 1mo ago Changed · +5 lines 7be4d9fbedca
- 1mo ago First seen · 43 lines · 61 tokens per session scan A 2ea421c901a2
run-manual-validation is a skill published in the GitHub repository fitlab-ai/agent-infra (86 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,952 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
round-verification
Verify a CCB execution round and produce a machine-readable round result artifact.
node-check
Verify one CCB worker node and reject hidden fallback, degradation, scope shrinkage, or missing evidence.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.