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 serejaris/kimi-skills --skill glab-runnergit clone --depth 1 https://github.com/serejaris/kimi-skillsWrote 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/serejaris/kimi-skills/glab-runner)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/glab-runner"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/glab-runner/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/serejaris/kimi-skills/glab-runner"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/glab-runner.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 | $0.00099 | $0.01459 |
| Opus 5 | $0.00049 | $0.00730 |
| Sonnet 5 | $0.00020 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
glab-runner 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 9d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
glab runner
通过命令行管理 GitLab CI/CD Runner(运行器)。
glab v1.87.0 新增
快速入门
# 列出当前项目的 Runner
glab runner list
# 暂停一个 Runner
glab runner pause <runner-id>
# 删除一个 Runner
glab runner delete <runner-id>
常见工作流
列出 Runner
# 列出当前项目的所有 Runner
glab runner list
# 列出指定项目的 Runner
glab runner list --repo owner/project
# 列出所有 Runner(实例级别,仅管理员可用)
glab runner list --all
# 以 JSON 格式输出
glab runner list --output json
# 分页查看
glab runner list --page 2 --per-page 50
JSON 输出解析示例:
# 查找所有已暂停的 Runner
glab runner list --output json | python3 -c "
import sys, json
runners = json.load(sys.stdin)
paused = [r for r in runners if r.get('paused')]
for r in paused:
print(f\"{r['id']}: {r.get('description','(no description)')} — {r.get('status')}\")
"
暂停 Runner
暂停 Runner 可以阻止它接收新作业,但不会将其移除。
# 暂停 Runner 123
glab runner pause 123
# 在指定项目上下文中暂停
glab runner pause 123 --repo owner/project
适合暂停的场景:
- 维护窗口期(更新、重启)
- 排查故障 Runner
- 临时减少 Runner 容量
- 退役前(先确认没有正在运行的作业)
删除 Runner
# 删除(会有确认提示)
glab runner delete 123
# 跳过确认直接删除
glab runner delete 123 --force
# 在指定项目上下文中删除
glab runner delete 123 --repo owner/project
⚠️ 删除操作不可恢复。 如果不确定,请先暂停。
决策树:暂停 vs 删除
是否需要永久移除该 Runner?
├─ 否 → 暂停它(可恢复)
└─ 是 → 它当前是否正在运行作业?
├─ 是 → 先暂停,等作业完成后再删除
└─ 否 → 使用 --force 直接删除
Runner 状态参考
| 状态 | 含义 |
|---|---|
online |
已连接,准备接收作业 |
offline |
未连接(检查 Runner 进程) |
paused |
已连接但不接收新作业 |
stale |
最近 3 个月无通信 |
故障排查
"runner: command not found":
- 需要 glab v1.87.0 或更高版本。使用
glab version检查。
实例级别 Runner 出现 "Permission denied":
- 实例级别的 Runner 管理需要 GitLab 管理员权限。
- 项目 Runner 可以由项目维护者管理。
Runner 无法暂停:
- 使用
glab runner list确认 Runner ID。 - 检查权限(至少需要项目的 Maintainer 角色)。
暂停后 Runner 仍显示 "online":
- Runner 进程仍在主机上运行——只是不再接收新作业。
- 这是正常现象。如需完全停止,请通过 SSH 登录 Runner 主机并停止进程。
无法删除 Runner:
- Runner 可能是共享/群组级别的(需要更高权限)。
- 检查 Runner 是否被分配给多个项目;从一个项目移除可能需要项目级别删除而非实例级别删除。
为项目分配/取消分配 Runner(v1.88.0+)
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.
- 9d ago First seen · 191 lines · 99 tokens per session scan A e72a8f2026e0
glab-runner is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,459 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 2026-09-03.
Other skills, from other repositories
review-tooling
Detect what dev tooling infrastructure a project has and flag gaps across linters, formatters, pre-commit hooks, test runners, and CI/CD pipelines. Returns structured findings without applying changes. Use when the user asks to "review tooling", "check project tooling", "what tooling is missing", "review dev…
ci-cd
Use when building or fixing a delivery pipeline. Covers pipeline structure, caching, test parallelization, deployment strategies, secrets, and making the pipeline fast enough that people do not route around it.
mobile-release
Use when preparing a mobile app for release. Covers versioning, signing, staged rollout, crash monitoring, store review requirements, and rollback when an update goes wrong.
neo-azure-pipelines
Use this skill when the user asks to create, review, debug, or modernize Azure Pipelines YAML for CI/CD, especially .NET builds, Azure App Service deploys, or IIS/on-premises deploys. Prefer bundled templates and verify task syntax against Microsoft docs when version-specific accuracy matters.
offensive-cicd-pipeline
Comprehensive CI/CD pipeline exploitation methodology covering GitHub Actions injection vectors (expression injection via PR titles and issue bodies, workflowrun event abuse, GITHUBTOKEN over-scoping, composite action supply chain compromise), Jenkins attack paths (Groovy sandbox escapes, script console remote code…
ci-preflight
Run before pushing any branch that adds shipped files, hooks, or platform-specific code. Prevents the CI-whiplash pattern — multiple red pushes that could have been caught locally.