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/backspace-shmackspace/claude-devkitWrote 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/backspace-shmackspace/claude-devkit/security-analyst)<a href="https://agentmods.dev/agents/backspace-shmackspace/claude-devkit/security-analyst"><img src="https://agentmods.dev/badge/agents/backspace-shmackspace/claude-devkit/security-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/backspace-shmackspace/claude-devkit/security-analyst"><img src="https://agentmods.dev/badge/agents/backspace-shmackspace/claude-devkit/security-analyst.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.01313 |
| Opus 5.5 | $0.00009 | $0.00525 |
| Sonnet 5.5 | $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 1mo 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 — 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.
- 1mo ago 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 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,313 once invoked, about $0.0001 per session on Opus 5.5. 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
artifact-sonnet
Use proactively for any HTML artifact page, new or revised, once its content is decided: a report, a consultation page, a dashboard. The page is written as a page SPEC (a .spec.md) and built; the agent never writes raw HTML for a new or revised page. Handoff: ONE page per brief, never two — a brief file with a named…
plugin-auditor
Launched by /aidex:aidex audit; not for direct use. Returns uninstall candidates by subagent cost vs usage.
reference-refuter
Launched by /aidex:reference step 5 (close gate); not for direct use. Returns a verdict per claim of a reference module.
web-researcher
Searches the web for a specific research query and returns a compressed finding with cohort-diverse citations and source-type annotations. Use when the parent recipe needs current-web information — especially fast-moving landscape/tooling topics where model priors can't be trusted.
regression-checker
Launched by /aidex:bugfix step 6; not for direct use. Returns whether the fix introduced regressions.
test-scout
Launched by /aidex:bugfix step 1; not for direct use. Returns the project's test framework and a regression-test approach.