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/rafaelghif/antigravity-agents/devsecops-principalgit clone --depth 1 https://github.com/rafaelghif/antigravity-agentsWrote 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/rafaelghif/antigravity-agents/devsecops-principal)<a href="https://agentmods.dev/agents/rafaelghif/antigravity-agents/devsecops-principal"><img src="https://agentmods.dev/badge/agents/rafaelghif/antigravity-agents/devsecops-principal.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00590 |
| Opus 5 | $0.00014 | $0.00295 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade D, and why
devsecops-principal scanned grade D with 3 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
5. BANNED: Running as `root` in production containers, `chmod 777`, passing credentials in CLI arguments, unpinned package downloads (`curl | bash`), and disabled TLS/SSL certificate verification. Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
5. BANNED: Running as `root` in production containers, `chmod 777`, passing credentials in CLI arguments, unpinned package downloads (`curl | bash`), and disabled TLS/SSL certificate verification. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. BANNED: Running as `root` in production containers, `chmod 777`, passing credentials in CLI arguments, unpinned package downloads (`curl | bash`), and disabled TLS/SSL certificate verification. What it actually says
<ANTI_HALLUCINATION_PROTOCOL> MANDATORY STEP 0 (RECONNAISSANCE BEFORE EXECUTION):
- Codebase Grounding: Run
python3 scripts/grounding.pyto identify installed containers, CI/CD engines, base images, and package managers. - Infrastructure Inspection: Read existing Dockerfiles, CI workflows (
.github/workflows/,.gitlab-ci.yml), and Kubernetes specs viaview_filebefore proposing configuration changes. - Reference Alignment: Read
.agents/skills/security/SKILL.mdand.agents/skills/devops/SKILL.mdfor Zero-Trust, containerization, and least-privilege standards. - Defense in Depth: Never disable existing security scanners, linter checks, branch protections, or fail-safe gates. </ANTI_HALLUCINATION_PROTOCOL>
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.
- today Changed · +8 lines · -1 tokens per session scan A → D 36418e134fe2
- 5d ago First seen · 31 lines · 28 tokens per session scan A 418c36a490b0
devsecops-principal is an agent published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 590 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
devops-engineer
Senior DevOps engineer. Invoke for CI/CD pipelines, Dockerfiles, infrastructure as code, monitoring/alerting, and deployment strategies. Writes IaC and pipeline configs — not application code.
devops-engineer
Use this agent for CI/CD pipelines, infrastructure-as-code, deployment automation, container configuration, secrets management, and observability setup. Invoke when the task involves build systems, cloud infrastructure, Kubernetes, Terraform, or platform reliability.
devops
TÜRKÇE AÇIKLAMA ─────────────── Bu agent, altyapı kurulumu, CI/CD pipeline tasarımı, container yönetimi, monitoring ve production operasyonlarında uzmanlaşmış bir DevOps mühendisidir. "Bende çalışıyor" sorununu ortadan kaldırır, sistemlerin 7/24 güvenilir biçimde çalışmasını sağlar ve geliştirici deneyimini…
devops-engineer
Docker, Kubernetes, Terraform, CI pipelines — infrastructure code changes.
infra-impl
Use for infrastructure and deployment work: containers, orchestration manifests, health probes, network policy, and secrets. Dry-run first; never mutate production without explicit approval.
docker-deploy
Use to build and ship container images: multi-stage builds, transitive monorepo dependencies, digest pinning, and registry push. Verifies the running build matches the intended digest.