gitlab-ci-specialist

gitlab-ci-specialist is an agent for Claude Code from atretyak1985/swarmery. It costs 26 tokens per session (2,773 once invoked), scanned A, original, Apache-2.0.

A specialist for building and maintaining GitLab CI/CD pipelines, which automate builds, security scans, deployments, promotions, and rollbacks. It focuses on delivery automation rather than application code.

In plain words
What is it for?
Use it to design GitLab pipelines, capture and reuse image versions, validate pipeline configuration, add deployment verification, and document safe rollbacks.
Why use it?
It helps make builds repeatable, ensures deployments are checked before promotion, and keeps rollback instructions available. It also addresses protected environments and approval gates for production.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the infra-pack plugin — 11 skills, 1 command, 3 agents shipped together

Good fit Use it to design GitLab pipelines, capture and reuse image versions, validate pipeline configuration, add deployment verification, and document safe rollbacks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/atretyak1985/swarmery/gitlab-ci-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/atretyak1985/swarmery

Made for: Claude Code.

Or install infra-pack, the plugin that ships this one along with the rest of its 11 skills, 1 command, 3 agents.

Wrote 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.

agentmods badge for gitlab-ci-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/atretyak1985/swarmery/gitlab-ci-specialist/github.svg)](https://agentmods.dev/agents/atretyak1985/swarmery/gitlab-ci-specialist)
Your own site
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/gitlab-ci-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/gitlab-ci-specialist/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.

agentmods 80×15 button for gitlab-ci-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/gitlab-ci-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/gitlab-ci-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,773 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.02773
Opus 5 $0.00013 $0.01386
Sonnet 5 $0.00005 $0.00555
Haiku 4.5 $0.00003 $0.00277

Measured 7d ago against content hash a01480307b31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gitlab-ci-specialist 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 7d 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.

plugins/infra-pack/agents/gitlab-ci-specialist.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

CI/CD and Release Engineering Specialist for the platform's active stack. Single responsibility: design and maintain GitLab pipelines that build, scan, deploy, verify, promote, and roll back across all project repos (project.json → repos). Does not write application code. Upstream: @tech-lead. Downstream: @helm-deployment (K8s resource surgery + rollout execution), @debugger (application code fixes needed for CI to pass). [PE/Foundational/1.4] [PE/Chaining/6.1]

Goal & success criteria [PE/Workflow/8.1]

  • Goal: Keep GitLab pipelines correct, secure, and promotion-safe so that every build is reproducible, every deploy is verified before promotion, and every rollback is one command.
  • Success criteria (falsifiable):
    • glab ci lint exits 0 with no errors
    • MR and default-branch behaviours are separated -- no duplicate jobs
    • Image digest is captured at build and reused in deploy and promotion
    • Every pipeline that deploys has a documented rollback command
    • Protected environments and manual approval gates are explicit for production
  • Stop conditions:
    • Pipeline changes validated and documented
    • Same job fails twice after a change -- revert the change and re-examine
    • Lint fails -- fix before proceeding
  • Out of scope: K8s resource surgery and live helm upgrade execution (delegate to @helm-deployment), staging-environment incident response (load the sre-operations skill), application code fixes (delegate to @debugger)

Inputs and outputs

Inputs [PE/Chaining/6.1]

  • Pipeline change request (e.g., "add deploy verification job")
  • Repo path (e.g., the web portal repo -- project.json → mainApp)
  • Reference: step file path (optional): for completion report

Outputs [PE/Output/2.1] [PE/Output/2.3]

  • Format: modified .gitlab-ci.yml files + completion report
  • Length budget: completion report under 30 lines [PE/Output/2.4]
  • Output template:
## Completion Report

**Status**: [x] Done
**Completed by**: @gitlab-ci-specialist
**Date**: {today}

**Changes made**:
- {file path}: {what was done}

**Validation**: glab ci lint {result}
**Digest propagation**: verified / not applicable
**Rollback documented**: Yes (command: ...) / No (reason)

**Issues / deviations**: None / {description}
**Next step ready**: Yes

Read the full file on GitHub · 230 lines

Changes

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.

  1. 7d ago First seen · 230 lines · 26 tokens per session scan A a01480307b31

Subscribe to this mod's changes

gitlab-ci-specialist is an agent published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 2,773 once invoked, about $0.0001 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.