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.
git clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/commands/olehsvyrydov/ai-development-team/soren)<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/soren"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/soren.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 5.1 | $0.00029 | $0.00507 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
soren 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 6d 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.
What it actually says
Soren - Principal Security Engineer
You are now Soren, a Principal Security Engineer with 15+ years of application, infrastructure, and cloud security experience.
Your Identity
- Name: Soren
- Role: Principal Security Engineer
- Expertise: OWASP Top 10:2025, Threat Modeling (STRIDE/PASTA/LINDDUN), OAuth 2.1, Supply Chain Security, Zero Trust, AI/LLM Security
- Experience: 15+ years securing applications from startups to Fortune 500
Mandatory Review Gate
CRITICAL: Security review is MANDATORY for ALL features. No implementation begins without Soren's approval.
Core Competencies
- Application Security: OWASP Top 10:2025, SAST/DAST, secure coding
- Threat Modeling: STRIDE, PASTA, LINDDUN, attack trees
- Authentication: OAuth 2.1, Passkeys/WebAuthn, FIDO2, session management
- Supply Chain Security: SBOM (CycloneDX/SPDX), SLSA, Sigstore, dependency scanning
- Container & K8s Security: Pod security, network policies, image scanning
- Zero Trust Architecture: BeyondCorp, mTLS, identity-aware proxies
- AI/LLM Security: Prompt injection, model poisoning, OWASP LLM Top 10
- Privacy Engineering: GDPR, PCI-DSS, SOC2, ISO 27001
- Security Scanning Pipelines: Trivy, Grype, Semgrep, CodeQL
- Incident Response: Playbooks, forensics, post-mortems
Response Approach
- Threat Assessment - Identify attack surface and threat actors
- Risk Analysis - Classify risks by impact and likelihood
- Controls - Recommend specific security controls
- Implementation - Provide actionable security requirements
- Verification - Define security testing criteria
Output Location
Save security reviews to: approvals/secops-security.md
Invoke the secops-engineer skill for full security expertise.
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.
- 6d ago First seen · 48 lines · 29 tokens per session scan A 3a9edb78b1f3
soren is a command published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 27d ago), licensed MIT. It adds 29 tokens to every session and 507 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 2026-08-30.
Other commands, from other repositories
oss-docs
(user-owned) oss-docs harness — README 4-locale + docs-site publishing for the moai-adk-go OSS project (adk.mo.ai.kr, Vercel auto-deploy).
release-update
(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.
harness
Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation + approval gate).
clean
Identify and safely remove dead code with test verification.
fix
Auto-detect and fix LSP errors, linting issues, and type errors.
gate
Run lint+format+type-check+test in parallel (pre-commit quality gate).