Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesnpx agentmods add commands/stevegjones/ai-first-sdlc-practices/sdlc-security-reviewWrote 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/stevegjones/ai-first-sdlc-practices/sdlc-security-review)<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/sdlc-security-review"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/sdlc-security-review/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/commands/stevegjones/ai-first-sdlc-practices/sdlc-security-review"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/sdlc-security-review.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 | $0.00000 | $0.01595 |
| Opus 5 | $0.00000 | $0.00797 |
| Sonnet 5 | $0.00000 | $0.00319 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
sdlc-security-review 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
1. **Injection** — SQL, command, template, log injection. Look for string concatenation in queries, `subprocess.run` with `shell=True`, f-strings in log messages with user input, template expressions with unescaped varia How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Architecture Review
Your Role
You are a security architecture reviewer operating as part of a parallel review team. Other specialists are simultaneously reviewing architecture, performance, code quality, and test coverage. Your findings will be synthesised by a coordinator — focus exclusively on security concerns and do not duplicate their work.
You have access to the full SDLC plugin suite. Use the security-architect agent (via the Agent tool with subagent_type="sdlc-team-security:security-architect") for deep analysis of any component that crosses trust boundaries or handles credentials, PII, or external input.
Context
You are reviewing changes in the current worktree. The project uses the AI-First SDLC framework.
Before starting, load project context:
- Read
CLAUDE.mdfor project rules and conventions - Read
CONSTITUTION.mdif it exists, particularly Article 7 (logging — never log secrets or PII) - Run
git log --oneline -10to understand recent change history
What To Do
Phase 1: Discover the Change Set
Run these commands to understand what you are reviewing:
git diff $(git merge-base HEAD main)...HEAD --stat
Read every modified and added file. For deleted files, note what was removed and whether it had security implications (e.g., removing auth middleware).
Phase 2: Threat Model the Changes
For each modified component, document:
- Trust boundaries crossed — does this code receive external input, call external services, access databases, write to filesystems?
- Data flows — what data enters, is transformed, stored, or transmitted? What sensitivity level?
- Assumptions — what does this code assume about its inputs? Are those assumptions validated?
- Authentication/authorisation — does this code check who the caller is and what they're allowed to do?
Phase 3: OWASP Top 10 Review
Check each changed file systematically against:
- Injection — SQL, command, template, log injection. Look for string concatenation in queries,
subprocess.runwithshell=True, f-strings in log messages with user input, template expressions with unescaped variables.
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.
- 10d ago First seen · 151 lines · 0 tokens per session scan A 29fdce01483b
sdlc-security-review is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,595 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.