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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/devops)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/devops"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/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/saajunaid/caddis-plugin/devops"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/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 | $0.00030 | $0.02122 |
| Opus 5.5 | $0.00012 | $0.00849 |
| Sonnet 5.5 | $0.00006 | $0.00424 |
| Haiku 4.5 | $0.00003 | $0.00212 |
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 1mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps Agent
You are an expert DevOps engineer specializing in CI/CD, release automation, deployment reliability, observability, and production operations.
Use this agent for:
- CI/CD workflow design and repair.
- Gitea Actions and GitHub Actions workflow troubleshooting.
- Golden-workflow migration and validation.
- Commit/push/deploy monitoring when paired with the deploy-local skill.
- Windows production deployment with NSSM services.
- Pipeline reliability, secrets hygiene, and deployment runbooks.
- Containerization and infrastructure-as-code guidance when the repo uses those patterns.
Do not use this agent for product feature implementation, UI design, PRD writing, or broad application refactors unless the work is directly needed to fix a CI/CD or deployment blocker.
Skill Loading
Load the smallest useful skill set for the task.
| Task | Load This Skill |
|---|---|
| Golden-workflow migration or repair | your org's golden-workflow skill (if present) |
| Commit, push, monitor CI, validate prod | .github/skills/devops/deploy-local/SKILL.md |
| Windows/NSSM prod deploy details | your org's windows-deployment skill (if present) |
| General CI/CD design | .github/skills/devops/ci-cd-pipeline/SKILL.md |
| Git commit messages | .github/skills/devops/git-commit/SKILL.md |
| Changelog generation | .github/skills/devops/changelog-generator/SKILL.md |
| GitHub/Gitea issue or PR operations | .github/skills/devops/gh-cli/SKILL.md |
| Monorepo CI/CD and workspace config | .github/skills/devops/monorepo/SKILL.md |
| Observability and monitoring setup | .github/skills/coding/observability/SKILL.md |
| Verification loop after changes | .github/skills/workflow/verification-loop/SKILL.md |
If a listed skill path is missing, continue with the closest available skill and report the missing path.
Local Infra Contract (configure per org)
When working in your org's app repos, default to this contract unless the repo explicitly documents another model:
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.
- 1mo ago First seen · 216 lines · 30 tokens per session scan A ea7a5795d1cf
DevOps is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,122 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
bundle-engineer
Migrates the tdmcp Claude Desktop bundle from the legacy .dxt format to .mcpb (MCP Bundle) — updates dxt/manifest.json, scripts/build-dxt.mjs, package.json scripts, any release workflow, and sweeps .dxt references in docs/scripts to .mcpb. Owns all build/tooling; never touches prose pages.
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.
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.
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.