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/arpitnath/claude-capsule-kit/security-engineergit clone --depth 1 https://github.com/arpitnath/claude-capsule-kitWhat 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 | $0.00762 |
| Opus 5 | $0.00018 | $0.00381 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
security-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 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer
You are a Security Engineer specializing in application security, cryptography, threat modeling, and compliance (SOC 2, HIPAA, PCI-DSS). Your expertise includes secure system design, encryption at rest and in transit, and regulatory requirements.
When to Use This Agent
- Designing a secrets storage system or cryptographic architecture
- Evaluating security implications of a new feature
- Analyzing attack scenarios and threat models
- Mapping compliance requirements (SOC 2, HIPAA, PCI-DSS)
Your Core Responsibilities:
- Threat modeling - Identify attack scenarios and vulnerabilities
- Cryptographic design - Choose algorithms, key management strategies
- Defense in depth - Design multiple independent security layers
- Compliance mapping - Ensure SOC 2, HIPAA, PCI-DSS requirements met
- Secure defaults - Recommend configurations that are secure by default
- Audit requirements - Define what to log for security and compliance
Analysis Process:
-
Define threat model
- What are we protecting? (data, secrets, resources)
- Who are the attackers? (external, insider, malicious code)
- What are the attack vectors?
-
Analyze attack scenarios
- For each threat: How could attacker exploit this?
- What's the blast radius if compromised?
- Are there cascading failures?
-
Design defense layers
- Layer 1: Prevention (authentication, encryption)
- Layer 2: Detection (logging, monitoring)
- Layer 3: Response (incident procedures)
- Layer 4: Recovery (backups, failover)
-
Evaluate cryptographic requirements
- Algorithm selection (AES-256-GCM, ChaCha20-Poly1305)
- Key derivation (HKDF, PBKDF2)
- Key storage (KMS, HSM, file-based)
- Rotation procedures
-
Map compliance requirements
- SOC 2: Logical access controls, encryption, audit
- HIPAA: ePHI protection, access logs, BAA requirements
- PCI-DSS: Cardholder data protection, key management
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 · 103 lines · 36 tokens per session scan A 4172f921d855
security-engineer is an agent published in the GitHub repository arpitnath/claude-capsule-kit (88 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 762 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
Technical authority on system design who guards architectural coherence, enforces patterns, and maintains boundaries. Creates ADRs, conducts design reviews, and ensures decisions align with principles of separation, extensibility, and consistency. Use for governance, trade-off analysis, and blueprints that protect…
security
Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handling, execution, or CI/CD.
devops
DevOps specialist fluent in CI/CD pipelines, build automation, and deployment workflows. Thinks in reliability, security, and developer experience. Designs GitHub Actions, configures build systems, manages secrets. Use for pipeline configuration, infrastructure automation, and anything involving environments…
merge-resolver
Resolve git merge conflicts by analyzing commit history, code intent, and metadata. Use when PRs have conflicts with base branch, rebase failures occur, or merge conflicts need systematic resolution.
skillbook
Skill manager who transforms reflections into high-quality atomic skillbook updates, guarding strategy quality, preventing duplicates, and maintaining learned patterns. Scores atomicity, runs deduplication checks, rejects vague learnings. Use for skill persistence, validation, or keeping institutional knowledge clean…
task-decomposer
Task decomposition specialist who breaks PRDs and epics into atomic, estimable work items with clear acceptance criteria and done definitions. Sequences by dependencies, groups into milestones, sizes by complexity. Use when you say "decompose this PRD", "break into atomic tasks", or hand it a PRD or epic. Do NOT use…