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 timwukp/agent-skills-best-practice --skill gitlab-ci-kiro-pipelinegit clone --depth 1 https://github.com/timwukp/agent-skills-best-practiceWrote 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/timwukp/agent-skills-best-practice/gitlab-ci-kiro-pipeline)<a href="https://agentmods.dev/skills/timwukp/agent-skills-best-practice/gitlab-ci-kiro-pipeline"><img src="https://agentmods.dev/badge/skills/timwukp/agent-skills-best-practice/gitlab-ci-kiro-pipeline/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/timwukp/agent-skills-best-practice/gitlab-ci-kiro-pipeline"><img src="https://agentmods.dev/badge/skills/timwukp/agent-skills-best-practice/gitlab-ci-kiro-pipeline.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 | $0.00207 | $0.03006 |
| Opus 5 | $0.00103 | $0.01503 |
| Sonnet 5 | $0.00041 | $0.00601 |
| Haiku 4.5 | $0.00021 | $0.00301 |
Grade B, and why
gitlab-ci-kiro-pipeline scanned grade B with 3 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 12d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- curl -fsSL https://cli.kiro.dev/install | bash Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- **`--trust-tools=read,grep`** grants only read-only tools. The agent can inspect the checked-out repo but cannot edit files or run arbitrary commands inside your runner. Widen this only deliberately. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- apt-get update && apt-get install -y curl git unzip How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab CI/CD Pipelines with Kiro CLI Headless Mode
Build .gitlab-ci.yml pipelines where Kiro CLI acts as an AI reviewer/analyst on merge requests. The pattern: each job installs Kiro CLI in a throwaway container, gathers context (the MR diff, config files, failure logs), and runs kiro-cli chat --no-interactive with a role-scoped prompt. Output goes to the job log and optionally gates the merge.
Workflow
- Understand the repo and goals. Ask (or infer from the repo) which checks the user wants: advisory review only, or merge-blocking gates? Which languages/config layouts exist? Is there an existing
.gitlab-ci.ymlto extend? - Pick jobs from the recipe catalog. Read
references/job-recipes.mdfor nine proven job patterns (code review, PII/secrets scan, test-failure analysis, diff issue detection, build-failure remediation, config drift, cross-repo config validation, duplication sync check, change-impact analysis). Copy only the ones the user needs. - Start from the template.
assets/gitlab-ci-template.ymlis a complete, working pipeline skeleton. Adapt stages and jobs rather than writing from scratch. - Decide advisory vs. gating per job (see below) and set
allow_failureaccordingly. - Verify prerequisites with the user: the
KIRO_API_KEYCI/CD variable must be set (masked, protected) in GitLab → Settings → CI/CD → Variables, and confirm your runners have internet access tohttps://cli.kiro.dev/install. If your GitLab Runner sandbox lives inside your VPC and has NO outbound internet access at all (no NAT gateway, no internet gateway, no proxy), refer to the "Air-gapped runners" section inreferences/kiro-cli-headless.mdfor the no-internet VPC approach — the API side works over AWS PrivateLink, but the CLI binary must be staged internally. - Lint before delivering. If the user has GitLab access, validate with the CI Lint API or
glab ci lint; otherwise at minimum check YAML validity (python3 -c "import yaml,sys; yaml.safe_load(open('.gitlab-ci.yml'))").
What ships with it
3 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.
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.
- 12d ago First seen · 136 lines · 207 tokens per session scan B f39c58315e4a
gitlab-ci-kiro-pipeline is a skill published in the GitHub repository timwukp/agent-skills-best-practice (10 stars, last pushed yesterday), licensed MIT. It adds 207 tokens to every session and 3,006 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 3 findings (downloads and executes remote code, unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
yds-software-evaluation
Evaluate code quality across five pillars (Architecture, Reliability, Observability, Security, DX) and produce a 1-10 scorecard with a strategic improvement roadmap. Use when you want a comprehensive quality review of a directory or module. Triggers on requests like "evaluate code quality", "review architecture"…
Code Review Checklist
Runs a systematic checklist review on any code diff or file, covering correctness, security, performance, and readability.
github-actions
GitHub Actions workflow review, scaffolding, and security hardening. Use when user says 'review my workflow', 'check my actions', 'scaffold a workflow', 'is my CI correct', 'pin actions', 'OIDC to AWS', or when working in .github/workflows/.yml files.
ci
GitLab CI/CD pipeline review and scaffolding for Terraform and Helm/EKS deployments, including individual stages, jobs, manual gates on prod stages, and pipeline credentials. Use when user says 'review my pipeline', 'check my gitlab-ci', 'scaffold a pipeline', 'is my CI correct', 'is my pipeline gated before prod'…
respond-goal
Use when the review-and-CI loop should continue through bounded rounds until no new actionable feedback remains.
github-actions-setup
Sets up automated CI/CD with GitHub Actions for any project in one pass. Intelligently auto-detects language (Node.js, Python, Go, Rust, Docker, Java, Ruby) and architecture (Frontend web apps vs Backend APIs/microservices). Generates production-ready workflow files for AWS, Vercel, Cloudflare, Railway, Render, or SSH…