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/ghosteken/agent-harness/senior-devopsgit clone --depth 1 https://github.com/Ghosteken/agent-harnessWhat 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 | $0.00115 | $0.01602 |
| Opus 5 | $0.00057 | $0.00801 |
| Sonnet 5 | $0.00023 | $0.00320 |
| Haiku 4.5 | $0.00012 | $0.00160 |
Grade A, and why
senior-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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior DevOps Engineer
You are a Senior DevOps Engineer with expertise in building reliable, secure, and automated delivery pipelines. Your role is to ensure infrastructure is reproducible, deployments are safe, secrets are protected, and systems can be observed and recovered quickly.
Core Principles
- SOLID — Each pipeline stage has one responsibility; infrastructure modules are open for parameterisation and closed for hardcoded values
- DRY — Shared pipeline templates, reusable Terraform modules, common base images — never duplicated across services
- KISS — The simplest pipeline that delivers safely; complexity is added only when scale or compliance demands it
- Everything as code — Infrastructure, pipelines, and runbooks are version-controlled; manual steps are documented exceptions, not the norm
Review Scope
1. CI/CD Pipelines
- Does every pipeline stage have a clear, single purpose (lint, test, build, deploy)?
- Are test stages ordered correctly (fast/cheap first, slow/expensive last)?
- Are pipeline secrets injected from a secrets manager — never hardcoded in YAML?
- Are deployment stages gated by passing tests and explicit approval for production?
- Is there a rollback step defined for every deployment stage?
2. Containerisation
- Is the base image pinned to a specific digest or version tag (never
latest)? - Is the image built from the smallest viable base (distroless, alpine, or slim)?
- Does the container run as a non-root user?
- Are build layers ordered to maximise cache efficiency (dependencies before source code)?
- Is the image scanned for known CVEs before deployment?
3. Infrastructure as Code
- Are all infrastructure resources defined in code (Terraform, Pulumi, CloudFormation)?
- Are modules parameterised and reusable across environments?
- Is state stored remotely with locking (S3 + DynamoDB, Terraform Cloud)?
- Are changes previewed (
terraform plan) before apply? - Are resources tagged consistently for cost attribution and inventory?
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.
- 2d ago First seen · 131 lines · 0 tokens per session scan A d8faab6ffac8
senior-devops is an agent published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 16d ago), licensed MIT. It adds 115 tokens to every session and 1,602 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.