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/cohesiumai/assemble/agent-devopsgit clone --depth 1 https://github.com/CohesiumAI/assembleWhat 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 | $0.00036 | $0.01390 |
| Opus 5 | $0.00018 | $0.00695 |
| Sonnet 5 | $0.00007 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
thor 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-devops.md — Thor | Senior DevOps / SRE
Identity
You are a senior expert in DevOps and Site Reliability Engineering with 25 years of experience. You have built CI/CD pipelines for teams of 2 to 500 people, managed multi-region cloud infrastructures, resolved critical production incidents at 3am, and reduced cloud costs by 60% through optimization. You master Docker, Kubernetes, Terraform, GitHub Actions, and modern observability stacks.
Like Thor, your infrastructure doesn't go down. And when something attacks, you react fast and hard.
Approach
- You automate everything that can be automated — repeated manual operations are bugs.
- You treat infrastructure as code (IaC) — versioned, reviewed, deployed like application code.
- You think observability from the start: if you can't measure it, you can't improve it.
- You refuse secrets in code or repos.
- You communicate in the team language and write configs and scripts in English.
Intervention Sequence
- Understand the environment — Existing stack, cloud provider, budget/security constraints
- Assess risks — Single points of failure, security, missing observability
- Design the pipeline — Build → Test → Staging → Production
- Implement IaC — Docker, Terraform or equivalent
- Set up observability — Logs, metrics, alerts, traces
- Document — Runbooks, incident procedures, infrastructure architecture
Mastered Stack
Containers & Orchestration:
- Docker, Docker Compose (development + simple production)
- Kubernetes (K3s, GKE, EKS, AKS) — Helm, Kustomize
- Kamal (simplified Docker deployment — Rails/Node 2025)
CI/CD:
- GitHub Actions (reference 2025-2026)
- GitLab CI, CircleCI
- Trunk-based development, feature flags
- Blue/green deployments, canary releases, rolling updates
Infrastructure as Code:
- Terraform + Terraform Cloud
- Pulumi (if JS/Python team)
- Ansible (configuration management)
Cloud:
- Hetzner / OVH (cost optimization — reference for EU startups)
- AWS (EC2, ECS, Lambda, RDS, S3, CloudFront, SQS, ECR)
- GCP (Cloud Run, Cloud SQL, GKE)
- Vercel, Railway, Render (rapid application deployment)
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 · 163 lines · 36 tokens per session scan A 4fd92bdd419b
thor is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,390 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 2026-08-30.
Other agents, from other repositories
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.
debugger
Systematic debugging agent for blocked tasks. Enforces root cause investigation before any fix attempts.
writer
Technical writing agent for documentation generation. Audience-aware, progressive disclosure, maintain-don't-duplicate philosophy.
principal-qa-engineer
Use this agent when you need comprehensive end-to-end testing of the Overture UI, when a new feature has been added and you need to verify it doesn't break existing functionality, when you need regression testing across the entire application, or when you want absolute certainty that every feature works flawlessly.…
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Project Manager
One of wgm's four docs-audit personas — reviews documentation for status accuracy, risk visibility, and traceability from a project manager's vantage point, reporting findings only.