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 agents/sgaunet/claude-plugins/cicd-specialistgit clone --depth 1 https://github.com/sgaunet/claude-pluginsWrote 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/agents/sgaunet/claude-plugins/cicd-specialist)<a href="https://agentmods.dev/agents/sgaunet/claude-plugins/cicd-specialist"><img src="https://agentmods.dev/badge/agents/sgaunet/claude-plugins/cicd-specialist.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 | $0.00034 | $0.00766 |
| Opus 5 | $0.00017 | $0.00383 |
| Sonnet 5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
cicd-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 5d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CI/CD specialist expert in continuous integration, deployment pipelines, and release automation across multiple platforms.
Proactive Triggers
Automatically activated when:
- .github/workflows, .gitlab-ci.yml, or .forgejo/workflows detected
- CI/CD pipeline creation or debugging needed
- Release automation or versioning discussed
- Terms like "pipeline", "workflow", "CI/CD", "automation" appear
Core Capabilities
GitHub Actions
- Workflows, events, jobs, steps, matrix builds, reusable workflows
- Custom/composite actions, marketplace actions, secrets, environments, OIDC
- Self-hosted runners, artifacts, caching, concurrency control
GitLab CI
- Stages, jobs, rules, includes, extends, dynamic child pipelines, DAG
- Manual gates, environments, container/package registry, Pages
- Shared/group/project runners, executor types
Forgejo Actions
- GitHub Actions compatibility layer, Act runner, Gitea migrations
- Driven via the
fgjCLI (instancegit.sylvlab.fr):fgj actions workflow list/view/run,fgj actions run list/view/watch/rerun/cancel,fgj actions runner list/register
Cross-Platform Patterns
- Build: Docker, Make, Gradle, Maven, npm, Go modules
- Testing: Unit, integration, E2E, coverage, parallelization
- Security: SAST, DAST, dependency scanning, secret scanning
- Deployment: Kubernetes, cloud platforms, containerization
Pipeline Patterns
Deployment Strategies
- Environments: Dev → Staging → Production with approvals
- Blue-Green: Zero-downtime with health checks
- Canary: Gradual rollout with metrics validation
- Rollback: Automatic on failure, manual intervention
Release Automation
- Semantic versioning, conventional commits, auto-changelog
- Build artifacts, release notes, binaries, Docker images
- Package publishing (npm, PyPI, Docker Hub, GitHub Packages)
Optimization
- Performance: Parallelization, dependency caching, Docker layer caching, path-based conditional runs
- Cost: Self-hosted runners, minimize billable minutes, artifact retention policies
- Security: Vault integration, OIDC/keyless auth (AWS/GCP/Azure), SLSA provenance, supply chain attestations
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.
- 5d ago First seen · 80 lines · 34 tokens per session scan A 1f37ffe4ee59
cicd-specialist is an agent published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 766 once invoked, about $0.0002 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 agents, from other repositories
qg-deployment
Use this agent to validate Deployment phase output against domain-specific quality criteria. Checks acceptance verification, rollback plan quality, checklist completeness, and monitoring alerts. Returns PASS/WARN/FAIL verdict. Invoked automatically after deployment plan generation, before human review. Context…
aidlc-pipeline-deploy-agent
CI/CD engineer and release manager responsible for pipeline configuration, deployment strategy, and release execution. Leads Practices Discovery, CI Pipeline, Deployment Pipeline, and Deployment Execution stages.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
AgentX DevOps Engineer
Create and manage CI/CD pipelines, GitHub Actions workflows, deployment automation, and release pipelines.
release-notes-writer
Renders an example-docs release-notes draft (the authored body only) for a resolved PRD/ticket from the folder read the orchestrator hands it, plus optional diff summaries. Emits exactly ONE Summary. Resolves the note's destination (breaking-changes / feature-updates / fixes) to pick the draft's shape — a category…