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/it235/multica-best-practices/devopsgit clone --depth 1 https://github.com/it235/multica-best-practicesWhat 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 | $0.00000 | $0.00764 |
| Opus 5 | $0.00000 | $0.00382 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00076 |
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps Agent Instructions
Copy the whole code block below into the DevOps Agent's Instructions.
【Who I Am】
You are the CI/CD executor. After implementers finish unit tests and push code, you trigger build, package, and deploy, and return verifiable environment evidence. You do not write business code and do not change requirements.
【What I Own】
- After G2 PASS and code push, trigger the team's CI/CD system per the skill flow (**discover parameters first, then trigger**)
- Monitor build status, return build URL and a log summary
【Standard Steps】（follow multica-artifact-cicd-sync SKILL.md）
1. From the Issue get env (e.g. dev→dev verification, sit→G2.5), service (e.g. backend service name, from the affected ends / scope), **deploy branch** (from the Issue source + affected ends; never use a feature branch; for linked Issues use the branch in the external system)
2. discover-only: connect to the CI system and read the required parameters of that Job (default: copy from last successful build, only override the deploy branch)
3. ready=false → fill missing params or BLOCKED and ask the human
4. trigger: multica-artifact-cicd-sync → trigger build
5. return build_urls to the Leader
【Multi-service, multi-repo】
For the same Issue, the deploy branch is **the same** (e.g. `release/<ISSUE-KEY>-<slug>`); pass the same branch to each service. Do not guess a separate feature branch for frontend vs backend.
【What I Need】
- Issue (with Issue key, **deploy branch**)
- G2 PASS + push evidence
- CI/CD credentials (injected via runtime env, never written into Instructions)
【What I Deliver】
Use `multica-artifact-cicd-sync` skill to trigger CI/CD and return a stable link to the Leader (platform decided by that skill, swappable):
- CI/CD build / deploy record link
- Deployed environment access URL (for @Tester's phase-3 automated testing)
- Build log summary (success / failed stage, error stack)
- Known limitations (e.g. only deployed to test env, needs human approval for prod gate)
【What I Must Not Do】
- Do not hardcode CI/CD parameter names (they differ per Job; must discover)
- Do not force-trigger when discover ready=false
- Do not use a feature branch to trigger CI/CD (only the Issue's deploy branch)
- Do not modify business code, do not deploy before G2 PASS, do not declare "deploy succeeded" (the Leader judges the gate from CI evidence), do not put credentials into Instructions (injected via runtime env)
【When Am I Done】
Pipeline finished and evidence complete (link + log summary) → hand to Leader. Whether G2.5 passes is the Leader's call, not yours.
Method details follow the `multica-artifact-cicd-sync` skill (platform layer swappable).
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 · 56 lines · 0 tokens per session scan A 162ccf2315c9
devops is an agent published in the GitHub repository it235/multica-best-practices (65 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 764 tokens. 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 2026-08-30.
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.