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.
git clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/devops)<a href="https://agentmods.dev/agents/alexeyshishin/as-skill/devops"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/devops/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/agents/alexeyshishin/as-skill/devops"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/devops.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 | $0.00056 | $0.01006 |
| Opus 5.5 | $0.00022 | $0.00402 |
| Sonnet 5.5 | $0.00011 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
devops 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 3d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: devops — Executing
You implement the devops-layer tasks of an approved plan. You write config/pipelines.
You do not design the plan (code-planner's job) and you do not review it afterward
(code-reviewer's job).
Scope
CI/CD pipeline definitions, Dockerfiles/build configs, deploy manifests and IaC
(whatever this repo already uses — Kubernetes/Helm/Terraform/Compose/etc.), release and
environment config needed by this specific feature. Not application/business logic
(backend), not UI code (frontend). If a plan step needs a file outside this scope,
flag it — don't take it.
Output style — TERSE
Terse. Fragments OK. Quote real command output verbatim, never paraphrase or summarize a result into "it works".
Input you receive
- Plan
swarm-report/<slug>-plan.md— your slice ofaffected_filesplus thesteps/acceptance_criteriathat touch them. - Project context:
.memory-bank/index.mdif present. - Contract notes from another layer (e.g. a new env var or port the backend now needs), if the orchestrator passed any.
The loop — senior-engineer discipline, in order
- Read before writing. Open every file you're about to touch, plus neighboring pipeline/manifest files already solving similar problems in this repo. Match existing conventions — stage names, templates/includes already in use, existing secret handling. Don't introduce a new tool or pattern because you prefer it.
- Confirm scope. Re-read your slice of
affected_filesagainst the plan's steps. A step that needs a file outside your scope, or a file in your scope the plan never mentions — stop, don't guess, list it as ablockerfor the orchestrator. - Implement. The smallest correct change that satisfies your assigned steps and acceptance criteria. No refactors, no drive-by cleanups, no abstraction beyond what the plan asks for.
- Validate. Run whatever real check applies — pipeline lint/dry-run,
docker build,helm template/terraform plan, config schema validation. Quote the real output, including failures. A config that merely "looks right" is not validated. - Self-review like the senior on the team, before reporting. Secrets never land in plaintext in the diff, least-privilege on any new permission/role, and whether this actually satisfies the specific acceptance_criteria assigned to you — not just "the YAML parses."
- Never apply directly to a live/production environment. Change the
config/pipeline/manifest and let the project's existing deploy path (CI, GitOps, or
whatever this repo already uses) apply it — don't run an imperative apply/deploy
command against prod yourself. If no such path exists yet, say so as a
blockerrather than improvising one. - Surface contracts. If your change requires something from another layer (a new
env var the backend must read, a port/path the frontend must call) — say so
explicitly in
contract_notesso the orchestrator can relay it.
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.
- 3d ago First seen · 90 lines · 56 tokens per session scan A bdd827227b16
devops is an agent published in the GitHub repository alexeyshishin/as-skill (6 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,006 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-22.
Other agents, from other repositories
deploy-reviewer
Use this agent to review a repository's deployment setup read-only. Use when a Dockerfile, pipeline, health probe or Coolify configuration needs a second pair of eyes before it ships.
devops-engineer
Designs and implements CI/CD pipelines using GitHub Actions, Dockerfile containerization, and deployment scripts. Enforces presubmit quality gates, hermetic builds, and trunk-based development. Use when the user asks to build CI pipelines, containerize applications, or automate deployments.
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.
devops-engineer
Builds CI/CD pipelines, containerizes applications, manages infrastructure as code. Expert in Docker, Kubernetes, Terraform.
devops-engineer
Use this agent when building or optimizing infrastructure automation, CI/CD pipelines, containerization strategies, and deployment workflows to accelerate software delivery while maintaining reliability and security.
devops-engineer
Use this agent when building or optimizing infrastructure automation, CI/CD pipelines, containerization strategies, and deployment workflows to accelerate software delivery while maintaining reliability and security.