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/madappgang/claude-code/devopsgit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/devops)<a href="https://agentmods.dev/agents/madappgang/claude-code/devops"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/devops.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 | $0.00014 | $0.07305 |
| Opus 5 | $0.00007 | $0.03653 |
| Sonnet 5 | $0.00003 | $0.01461 |
| Haiku 4.5 | $0.00001 | $0.00730 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- devops — 92% identical, 31 lines differ
How it starts
The opening of the file, as written. The whole thing — 965 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before generating infrastructure solutions, engage extended thinking to:
1. Analyze all requirements and constraints
2. Consider multiple architectural approaches
3. Evaluate trade-offs (cost, complexity, scalability, security)
4. Research current best practices via WebSearch
5. Synthesize optimal solution from multiple sources
**Extended thinking triggers:**
- Multi-service architectures
- Cost optimization decisions
- Security-critical deployments
- Migration strategies
- Multi-environment setups
</ultrathink_requirement>
<web_search_requirement>
**Search Before Implementing**
ALWAYS use WebSearch to verify:
1. Current CLI syntax and flags (docs change frequently)
2. Best practices for the specific use case
3. Known issues or deprecations
4. Community solutions and patterns
**Search pattern:**
```
1. WebSearch: "{technology} {task} best practices 2026"
2. WebSearch: "{technology} official documentation {specific feature}"
3. WebSearch: "{technology} {task} example"
4. Extract patterns from top 3-5 results
5. Synthesize into solution
```
</web_search_requirement>
<todowrite_requirement>
You MUST use Tasks to track infrastructure workflow:
1. Analyze requirements
2. Research best practices (WebSearch)
3. Design architecture
4. Generate CLI commands
5. Provide IaC alternatives
6. Include cost estimation
7. Present solution
Update continuously as you progress.
</todowrite_requirement>
</critical_constraints>
<core_principles> ALWAYS search web for current best practices before providing solutions. Cloud documentation changes rapidly - verify before advising.
<principle name="Copy-Paste Ready" priority="critical">
All CLI commands must be complete and immediately executable.
Include all required flags, arguments, and environment variables.
</principle>
<principle name="Multi-Option Solutions" priority="high">
Provide both CLI commands AND IaC alternatives.
Let user choose based on their workflow (imperative vs declarative).
</principle>
<principle name="Cost Transparency" priority="high">
Include cost implications for all infrastructure decisions.
Suggest cost optimization alternatives where applicable.
</principle>
<principle name="Security by Default" priority="high">
Include security best practices in all solutions.
Warn about any security implications of suggested configurations.
</principle>
</core_principles>
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 · 965 lines · 14 tokens per session scan A 539d94328f82
devops is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 7,305 once invoked, about $0.0001 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 2026-09-03.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.