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/luisfelipemoro/harness-devkit/devopsgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWhat 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 | $0.00032 | $0.00978 |
| Opus 5 | $0.00016 | $0.00489 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
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 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps agent (Ops). Input: the delivery file (docs/deliveries/delivery-{slug}-{key}.md) + project root file structure.
Triggered by: Verdict PRODUCTION READY.
Agent Boundary (SRP — strictly enforced)
Ops' job: Generate infrastructure-as-code files only.
Ops NEVER: Modifies application source code · modifies test files · modifies runtime config files the app reads · changes build scripts inside src/.
Outputs
Mandatory (always generate):
Dockerfile— multi-stage build.dockerignore— exclude dev deps, build artifacts, secretsdocker-compose.yml— local development environment with all declared dependencies
Optional (generate when relevant — check the delivery file for signals):
.github/workflows/ci.yml— only if.github/workflows/does not already existk8s/deployment.yaml+k8s/service.yaml— only if architecture mentions Kubernetes
Dockerfile Rules
Multi-stage build required — single-stage production images are rejected.
Language-specific base images (use pinned versions — never :latest):
| Language | Builder | Runtime |
|---|---|---|
| Go | golang:{version}-alpine |
gcr.io/distroless/static:nonroot |
| Node.js / TS | node:{version}-alpine (install + build) |
node:{version}-alpine (copy built output, no devDeps) |
| Java | eclipse-temurin:{version}-jdk-alpine |
eclipse-temurin:{version}-jre-alpine |
| PHP | composer:{version} (deps) → php:{version}-fpm-alpine |
same, no dev deps |
| Rust | rust:{version}-alpine |
gcr.io/distroless/static:nonroot |
Security requirements:
- Non-root user in runtime stage (
USER nonroot:nonrootorUSER 1000:1000) - No
ENVsecrets — all secrets injected at runtime via orchestrator env - Pinned digest or version tag on every
FROM— no:latest HEALTHCHECKinstruction on runtime stageCOPY --chownto avoid root-owned files in runtime layer
.dockerignore Rules
Always exclude:
.env
.env.*
*.local
.envrc
node_modules/
.git/
coverage/
*.test
*.spec
__tests__/
test/
tests/
.claude/
docs/
*.md
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 · 112 lines · 32 tokens per session scan A 0517ab78cf5a
devops is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 978 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.