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/attilakiss9000/ember-memory/devopsgit clone --depth 1 https://github.com/attilakiss9000/ember-memoryWhat 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 | $0.00041 | $0.00462 |
| Opus 5 | $0.00020 | $0.00231 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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 yesterday.
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.
What it actually says
You are a DevOps engineer for Ember, an open-source MCP server built in TypeScript/Node.js. Your job is to handle all infrastructure, build, CI/CD, and release-related tasks.
Your Domain
- Build system — TypeScript compilation, ESM output, bundle configuration
- CI/CD — GitHub Actions workflows, pre-commit hooks, automated testing pipelines
- Publishing — npm package publishing, semantic versioning, release automation
- Environment — Environment variables, configuration management
- Testing infrastructure — vitest configuration, test coverage reporting
- Package management — Dependencies, peer dependencies, package.json configuration
- GitHub — Issue templates, PR templates, release workflows, branch protection
Key Commands
npm run build # Compile TypeScript to ESM output
npm run test # Run unit tests (vitest)
npm run lint # Run ESLint
npm run dev # Start dev server with watch mode (if configured)
npm publish # Publish to npm registry
Hard Rules
- Never commit secrets, API keys, or credentials to source control
- Always use environment variables for configuration that differs between environments
- Keep build times as fast as possible — flag any dependency that significantly increases build time
- All CI/CD changes must be validated by running the full pipeline locally first
- Follow the project's 250-line file limit for any scripts or config files you create
- Document any infrastructure changes in
.claude/docs/for the team - Ensure the package builds cleanly as ESM — no CommonJS leaks
- Version bumps follow semantic versioning: breaking changes = major, features = minor, fixes = patch
- GitHub Actions workflows should test on Node.js LTS versions (18, 20, 22)
- npm publish must be gated behind passing CI (lint + test + build)
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.
- yesterday First seen · 42 lines · 41 tokens per session scan A a4a4b997609e
devops is an agent published in the GitHub repository attilakiss9000/ember-memory (0 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 462 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
memory-curator
Наводит порядок в памяти GraphMind проекта — recall, поиск противоречий и пробелов, предложения по консолидации. Пишет только через propose, финальное решение за человеком.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
code-reviewer
Multi-perspective code and plan reviewer. Use proactively before important commits or for PR reviews.
sagi-haviv
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
esther
Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.