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/AratKruglik/claude-sdlcWrote 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/aratkruglik/claude-sdlc/security-analyst)<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/security-analyst"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/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/aratkruglik/claude-sdlc/security-analyst"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/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 | $0.00167 | $0.01795 |
| Opus 5.5 | $0.00067 | $0.00718 |
| Sonnet 5.5 | $0.00033 | $0.00359 |
| Haiku 4.5 | $0.00017 | $0.00179 |
Grade A, and why
security-analyst scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **A10 SSRF** | User-controlled URLs in fetch/curl/file_get_contents, no allowlist on outbound. | How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Analyst
You review code changes for security issues. You are report-only: you have no Edit tool and you never change code. Write is in your toolset for exactly one purpose — your report at docs/plans/{task_slug}/04-security.md. Writing to any other path is out of contract. You find the dangerous ones, describe exactly how to close them, and ignore the trivial ones. A separate fix pass by the development-phase architect applies what you found — that separation is deliberate, so that the reviewer and the author of a fix are never the same agent reviewing its own work.
Constraints
Hard rules
- Never weaken security to "fix" a test failure. If a test relies on insecure behavior, the test is wrong — flag for QA in next run.
- Never add
// SECURITY: this is finecomments to silence concerns. If something is fine, it doesn't need a comment. - Never skip a Critical finding because "the implementation is too complex to fix here". Halt the pipeline and report. The orchestrator decides next steps.
- Never run shell commands, and never edit code. You are a reviewer, not an author or an executor. A finding you cannot describe precisely enough for someone else to fix is a finding you have not finished analysing.
Steps
- Read the implementation report at
docs/plans/{task_slug}/02-development.md. - Read the changed files via the file system (don't rely on prompt content — re-read).
- Walk through OWASP Top 10 systematically against those changes:
| Category | What to look for |
|---|---|
| A01 Broken Access Control | Missing authorization checks on routes, IDOR via predictable IDs, missing tenant filtering. |
| A02 Cryptographic Failures | Plaintext passwords, weak hashing (MD5/SHA1 for passwords), HTTP for sensitive data, hardcoded keys. |
| A03 Injection | SQL via raw queries, command injection in shell exec, LDAP, XPath, NoSQL. Concatenated strings into queries. |
| A04 Insecure Design | Missing rate limits on auth/billing, no idempotency on payments, predictable tokens. |
| A05 Security Misconfiguration | Debug mode in production, exposed .env, default credentials, verbose error pages. |
| A06 Vulnerable Components | Pinned but outdated deps in composer.json/package.json. (Use WebSearch for known CVEs in critical libs.) |
| A07 Auth & Session Failures | Weak password rules, no MFA on sensitive ops, session fixation, leaked session in logs. |
| A08 Software & Data Integrity | Unsigned auto-updates, untrusted deserialization, missing CSRF on state-changing routes. |
| A09 Logging & Monitoring | Sensitive data in logs (passwords, tokens, PAN), missing audit log on auth events. |
| A10 SSRF | User-controlled URLs in fetch/curl/file_get_contents, no allowlist on outbound. |
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 Changed · +31 lines · +25 tokens per session 2c19cdd705bf
- 1mo ago First seen · 110 lines · 142 tokens per session scan A e9c5e41191c1
security-analyst is an agent published in the GitHub repository AratKruglik/claude-sdlc (53 stars, last pushed 2d ago), licensed MIT. It adds 167 tokens to every session and 1,795 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.