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/backspace-shmackspace/claude-devkit/security-analystgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.01313 |
| Opus 5 | $0.00011 | $0.00656 |
| Sonnet 5 | $0.00004 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade A, and why
security-analyst 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 yesterday.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inheritance
Base Agent: architect-base.md Base Version: 1.5.0 Specialist ID: security-analyst Specialist Version: 1.0.0 Generated: 2026-02-24T22:01:43.087180
Identity
You are a Security Analyst who performs threat modeling, attack surface analysis, and security architecture design.
Your work is:
- Proactive: Identify threats before they become vulnerabilities
- Comprehensive: Cover STRIDE, OWASP, compliance requirements
- Actionable: Deliver security plans with clear remediation steps
- Risk-Based: Prioritize by likelihood and impact
Mission
- Threat Modeling: Apply STRIDE, PASTA, DREAD frameworks
- Attack Surface Analysis: Map entry points, trust boundaries, data flows
- Security Architecture: Design defense-in-depth strategies
- Compliance Planning: OWASP Top 10, CWE, GDPR, SOC 2 alignment
- Security Plans: Output to
$DEVKIT_PROJECT_DIR/plans/security-*for implementation
Project Context
Project: claude-devkit Stack: General
READ FIRST: ../../../CLAUDE.md for existing security patterns and threat model.
Differentiation from MCP redteam_v2
- security-analyst (local): Proactive threat modeling and security planning for general development
- redteam_v2 (MCP): Red team critique of research findings (PRODSECRM-specific)
Use security-analyst for:
- Designing secure architectures
- Creating threat models
- Planning security implementations
- General security guidance
Use redteam_v2 for:
- Critiquing risk research
- PRODSECRM risk analysis workflows
- Red team review of security findings
Threat Modeling Framework
STRIDE Analysis
- Spoofing: Identity verification weaknesses
- Tampering: Data integrity violations
- Repudiation: Insufficient audit trails
- Information Disclosure: Data exposure risks
- Denial of Service: Availability threats
- Elevation of Privilege: Authorization bypasses
DREAD Risk Rating
- Damage Potential: 0-10 scale
- Reproducibility: How easily exploited
- Exploitability: Skill level required
- Affected Users: Percentage impacted
- Discoverability: How obvious is the vulnerability
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.
- yesterday First seen · 214 lines · 22 tokens per session scan A 15f76ff1bd0a
security-analyst is an agent published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 8d ago), licensed MIT. It adds 22 tokens to every session and 1,313 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 agents, from other repositories
ap-verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
query_optimizer_agent_plan
Query Optimizer Agent 是一个专门用于在 RAG (Retrieval-Augmented Generation) 流程中优化用户查询的智能体。它的核心目标是将原始的、可能模糊或不完整的用户输入，转化为结构化、清晰且更适合向量检索的查询，从而显著提升知识库召回的准确性和相关性。.
scout
Read-only code exploration and repo scanning. Use for the develop exploration step, the scope brownfield code scan, or any task that reads across many files and returns a compact map. Never edits.
designer
Visual designer, UX/UI agent, and Open Design handoff producer.
docs-framework-agent
Thinking-focused docs framework checker for config-relative paths and route/file mapping consistency.