Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/akin-ozer/cc-devops-skillsnpx agentmods add skills/akin-ozer/cc-devops-skills/gitlab-ci-generatorWrote 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/akin-ozer/cc-devops-skills/gitlab-ci-generator)<a href="https://agentmods.dev/skills/akin-ozer/cc-devops-skills/gitlab-ci-generator"><img src="https://agentmods.dev/badge/skills/akin-ozer/cc-devops-skills/gitlab-ci-generator.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.09916 |
| Opus 5 | $0.00012 | $0.04958 |
| Sonnet 5 | $0.00005 | $0.01983 |
| Haiku 4.5 | $0.00002 | $0.00992 |
Grade A, and why
gitlab-ci-generator scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| curl --header "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 1,217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab CI/CD Pipeline Generator
Overview
Generate production-ready GitLab CI/CD pipeline configurations following current best practices, security standards, and naming conventions. All generated resources are automatically validated using the devops-skills:gitlab-ci-validator skill to ensure syntax correctness and compliance with best practices.
Trigger Phrases
Use this skill when the user asks for GitLab CI/CD generation requests such as:
- "Create a
.gitlab-ci.ymlfor..." - "Build a GitLab pipeline for Node/Python/Java..."
- "Add Docker build and deploy jobs in GitLab CI"
- "Set up GitLab parent-child or multi-project pipelines"
- "Include SAST/dependency scanning templates in GitLab CI"
Execution Model
Follow this deterministic flow in order:
- Classify request complexity (
targeted,lightweight, orfull). - Load only the required reference tier for that complexity.
- Output the matching response profile for the selected mode.
- For complete pipeline generation, start from the closest template and customize.
- Validate complete pipelines with strict Critical/High gates.
- Present output with validation status and template/version notes.
If tooling is unavailable, use the documented fallback branch and report it explicitly.
Mode Routing (Quick Decision)
| Request shape | Mode | Required references | Output profile |
|---|---|---|---|
| Simple single-file pipeline with common jobs/stages and low risk | Lightweight | Tier 1 (+ Tier 2 only if needed) | Lightweight confirmation + compact final sections |
Multi-environment deploy, advanced rules, includes/templates, security/compliance-sensitive workflow, or unclear/risky requirement |
Full | Tier 1 + Tier 2 (Tier 3 only if needed) | Full confirmation + full final sections |
| Review/Q&A/snippet/focused fix (not full file generation) | Targeted | Only directly relevant files | Concise targeted response (no full boilerplate) |
What ships with it
10 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.
- .gitignore 22 B
- assets/templates/basic-pipeline.yml 7.7 KB
- assets/templates/docker-build.yml 8.6 KB
- assets/templates/kubernetes-deploy.yml 11 KB
- assets/templates/multi-project.yml 8.2 KB
- references/best-practices.md 17 KB
- references/common-patterns.md 20 KB
- references/gitlab-ci-reference.md 18 KB
- references/security-guidelines.md 16 KB
- tests/test_skill_contract.py 4.5 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.
- 6d ago First seen · 1,217 lines · 23 tokens per session scan A 5933f0ba4ba5
gitlab-ci-generator is a skill published in the GitHub repository akin-ozer/cc-devops-skills (306 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 9,916 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.