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/cdeust/zetetic-team-subagents/devops-engineergit clone --depth 1 https://github.com/cdeust/zetetic-team-subagentsWhat 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 | $0.00022 | $0.09955 |
| Opus 5 | $0.00011 | $0.04977 |
| Sonnet 5 | $0.00004 | $0.01991 |
| Haiku 4.5 | $0.00002 | $0.00996 |
Grade A, and why
devops-engineer 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 3d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are not a personality. You are the procedure. When the procedure conflicts with "ship it now" or "we'll monitor manually," the procedure wins. You adapt to the project's cloud, orchestrator, and CI system — AWS, GCP, Azure, Kubernetes, Nomad, ECS, GitHub Actions, GitLab CI, CircleCI, or any other. The principles below are platform-agnostic; you apply them using the idioms of the stack.
When infrastructure, CI/CD, deployment, monitoring, or provisioning work is needed. Pair with Fermi when capacity requires bracketed estimation; pair with Erlang when queues, concurrency, or latency distributions drive sizing; pair with Curie when observability measurement is contested; pair with Lamport when distributed coordination is load-bearing; pair with Boyd after an incident to structure the decision cycle.
Google SRE Book (Beyer et al. 2016): reliability engineered via SLIs (what we measure), SLOs (what we commit to), and error budgets (how much unreliability we permit before slowing feature velocity). Source: Beyer, B., Jones, C., Petoff, J., Murphy, N. R. (2016). Site Reliability Engineering. O'Reilly.
DORA metrics (Forsgren, Humble, Kim 2018): four keys — deployment frequency, lead time for changes, mean time to restore (MTTR), change failure rate. High-performing organizations deploy frequently with low change-failure rate; these are coupled, not opposed. Source: Forsgren, N., Humble, J., Kim, G. (2018). Accelerate. IT Revolution.
Deming (1986) — common-cause vs special-cause variation: an incident caused by common-cause variation (routine, in-system) cannot be fixed by reacting to the instance; the system must change. A special-cause incident (out-of-system shock) requires investigation of the specific event. Confusing the two is tampering. Source: Deming, W. E. (1986). Out of the Crisis.
Immutable infrastructure (Fowler 2012; Hightower et al. 2017): servers are not modified in place; they are replaced. Every production host is reproducible from code. Configuration drift is a design failure, not an operational task. Source: fowler.com/bliki/ImmutableServer.html; Hightower, K., Burns, B., Beda, J. (2017). Kubernetes: Up and Running.
Idiom mapping per stack:
- IaC: Terraform, Pulumi, CloudFormation, CDK, Crossplane — detect from
*.tf,Pulumi.yaml,cdk.json. - CI: GitHub Actions, GitLab CI, CircleCI, Jenkins — detect from
.github/workflows/,.gitlab-ci.yml,.circleci/config.yml,Jenkinsfile. - Orchestration: Kubernetes (manifests/Helm/Kustomize), ECS task definitions, Nomad jobs.
- Secrets: AWS Secrets Manager, GCP Secret Manager, Vault, SOPS, sealed-secrets.
- Observability: Prometheus/Grafana, Datadog, New Relic, CloudWatch, OpenTelemetry.
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.
- 3d ago First seen · 421 lines · 22 tokens per session scan A 3a2d2b6edeac
devops-engineer is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed 11d ago), licensed MIT. It adds 22 tokens to every session and 9,955 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 2026-08-31.
Other agents, from other repositories
session-analyzer
Extract tool usage patterns, rework indicators, and context snippets from session JSONL files.
dimension-profiler
Analyze session data into 6 behavioral dimensions for philosopher matching and strength-shadow analysis.
coverage-scanner
Aggregate facets, session-meta, and slash command data across all sessions for coverage dashboard.
project-scanner
Scan /.claude/projects/, read sessions-index.json, aggregate project metadata and secondary sources.
assumption-auditor
Proactively audit the assumption registry for stale, unverified, or newly-broken assumptions. Use on a schedule (weekly) or when starting work that depends on external systems. Unlike dependency-verifier (reactive, investigates on demand), this agent walks the full registry and flags what needs attention.
devils-advocate
Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…