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 skills/zapier/connectors/gitlabnpx skills add zapier/connectors --skill gitlabgit clone --depth 1 https://github.com/zapier/connectorsWhat 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 | $0.00064 | $0.04892 |
| Opus 5 | $0.00032 | $0.02446 |
| Sonnet 5 | $0.00013 | $0.00978 |
| Haiku 4.5 | $0.00006 | $0.00489 |
Grade A, and why
gitlab 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- .claude-plugin/plugin.json 908 B
- .mcp.json 128 B
- CHANGELOG.md 1.8 KB
- cli.js 7.3 KB runs code
- cli.ts 141 B runs code
- connections.ts 1.7 KB runs code
- evals/evals.json 22 KB
- evals/results.md 2.7 KB
- index.ts 6.4 KB runs code
- lib/gitlab.ts 2.0 KB runs code
- LICENSE 3.8 KB
- NOTICE 444 B
- package.json 1.5 KB
- README.md 14 KB
- references/gitlab-api-gotchas.md 8.7 KB
- references/gitlab-formatting.md 2.4 KB
- references/use-as-cli.md 2.8 KB
- references/use-as-mcp.md 2.6 KB
- references/use-as-recipe.md 5.7 KB
- references/use-as-sdk.md 1.2 KB
- references/use-with-zapier.md 6.3 KB
- references/use-without-zapier.md 3.2 KB
- scripts/addIssueComment.ts 1.6 KB runs code
- scripts/addMergeRequestComment.ts 1.7 KB runs code
- scripts/addMergeRequestDiffComment.ts 2.4 KB runs code
- scripts/approveMergeRequest.ts 1.6 KB runs code
- scripts/cancelPipeline.ts 1.4 KB runs code
- scripts/commitFiles.ts 2.7 KB runs code
- scripts/compareRefs.ts 1.8 KB runs code
- scripts/createBranch.ts 1.7 KB runs code
- scripts/createIssue.ts 2.5 KB runs code
- scripts/createMergeRequest.ts 2.9 KB runs code
- scripts/createWorkItem.ts 3.6 KB runs code
- scripts/findUsers.ts 2.1 KB runs code
- scripts/getCurrentUser.ts 1.1 KB runs code
- scripts/getFile.ts 1.7 KB runs code
- scripts/getIssue.ts 1.7 KB runs code
- scripts/getJobLog.ts 1.3 KB runs code
- scripts/getMergeRequest.ts 1.8 KB runs code
- scripts/getMergeRequestDiffs.ts 2.1 KB runs code
- scripts/getPipeline.ts 1.4 KB runs code
- scripts/getProject.ts 1.5 KB runs code
- scripts/getWorkItem.ts 2.2 KB runs code
- scripts/listBranches.ts 1.9 KB runs code
- scripts/listCommits.ts 2.3 KB runs code
- scripts/listGroupMergeRequests.ts 3.1 KB runs code
- scripts/listIssues.ts 3.0 KB runs code
- scripts/listLabels.ts 1.7 KB runs code
- scripts/listMergeRequestCommits.ts 1.7 KB runs code
- scripts/listMergeRequestDiscussions.ts 2.9 KB runs code
- scripts/listMergeRequestNotes.ts 2.0 KB runs code
- scripts/listMergeRequests.ts 2.9 KB runs code
- scripts/listMilestones.ts 1.7 KB runs code
- scripts/listPipelineJobs.ts 1.9 KB runs code
- scripts/listPipelines.ts 2.3 KB runs code
- scripts/listProjectMergeRequests.ts 3.1 KB runs code
- scripts/listProjects.ts 2.6 KB runs code
- scripts/listRepositoryTree.ts 2.3 KB runs code
- scripts/listWorkItems.ts 3.2 KB runs code
- scripts/mergeMergeRequest.ts 2.5 KB runs code
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 · 208 lines · 64 tokens per session scan A 4baef4222144
gitlab is a skill published in the GitHub repository zapier/connectors (163 stars, last pushed 7d ago), with no licence file. It adds 64 tokens to every session and 4,892 once invoked, about $0.0003 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 skills, from other repositories
lattice-init
Guided setup and upgrade-check experience for Lattice projects -- scans the repository, detects existing configuration and outdated conventions, suggests refiners and available upgrades in priority order, and creates or reconciles the .lattice/ config. Bridges the gap between installing skills and getting first value…
intelligent-investor-graham
Use Graham value investing for Is this investment or speculation, defensive stock screens, margin of safety, Mr. Market, allocation, funds, IPOs.
skill-to-workflow
将现有 Skill、Prompt、SOP 或 Agent 操作说明拆解为可执行、可监控、可重试的 Workflow 规格；识别真实节点、共享子工作流、工具调用、状态、分支、循环、 提示词、数据契约和验收方式。适用于用户要求把一个 Skill 转成工作流、节点图、 编排方案或 Workflow 实现规格时；不替代原 Skill 执行业务任务，也不在未要求时 绑定具体工作流平台或直接部署。.
query-loop-implementation
Implement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, toolresult feedback, max-turn exits, or Claude Code-like Agent Loop behavior…
documentation-and-adrs
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
daily-life-discovery
Guide a consent-based conversation that helps a person discover how an AI agent could improve their day-to-day life: routines, friction, attention, decisions, relationships, learning, and small experiments. Use when someone asks for a daily check-in, wants the agent to learn how they work, says "grill me," wants a…