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 commands/alphaaiservice/cortex/code-reviewgit clone --depth 1 https://github.com/alphaaiservice/cortexWhat 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 | $0.00032 | $0.01052 |
| Opus 5 | $0.00016 | $0.00526 |
| Sonnet 5 | $0.00006 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
code-review 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automated Code Review
You are a senior code reviewer performing a thorough review. Analyze: $ARGUMENTS
Step 1: Identify Changes
# If --staged or no args, review staged changes
git diff --cached --name-only 2>/dev/null || git diff --name-only HEAD~1
# If branch name provided, compare against main
git diff main...$ARGUMENTS --name-only 2>/dev/null
Read every changed file completely.
Step 2: Multi-Dimensional Review
Use Agent tool (mode = "bypassPermissions") to run 5 parallel review agents:
Agent 1: Code Quality
- Clean code principles (SRP, DRY, KISS)
- Function/method length and complexity
- Naming conventions consistency
- Magic numbers and hardcoded values
- Dead code or unused imports
- Proper error handling
- Resource cleanup (connections, file handles)
Agent 2: Security Analysis
- SQL injection vectors
- XSS vulnerabilities
- Authentication/authorization gaps
- Sensitive data exposure (API keys, passwords)
- Input validation completeness
- CORS configuration
- Dependency vulnerabilities (check package versions)
Agent 3: Performance Review
- N+1 query patterns
- Missing database indexes (if schema changes)
- Unnecessary re-renders (React)
- Memory leaks (event listeners, subscriptions)
- Unbounded data fetching
- Missing pagination
- Caching opportunities
Agent 4: Testing Assessment
- Test coverage for new code
- Edge case coverage
- Mock appropriateness
- Test isolation
- Missing negative test cases
- Integration test gaps
Agent 5: Architecture & Standards
- Consistent with existing patterns
- CLAUDE.md / STANDARDS.md compliance
- API contract changes (breaking changes?)
- Proper abstraction layers
- Dependency direction (no circular deps)
- Documentation updates needed
Agent Teams Review Mode (When Enabled)
When CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set, upgrade to Agent Teams review mode where the 5 reviewers become real teammates who debate and challenge each other's findings.
Team Creation:
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 · 131 lines · 32 tokens per session scan A 3c36d01efe60
code-review is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 32 tokens to every session and 1,052 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 2026-08-31.
Other commands, from other repositories
alfred
Asistente contextual de Alfred Dev. Enruta automáticamente al flujo o comando operativo correcto.
feature
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega.
_composicion
Protocolo interno compartido para la composición dinámica del equipo de Alfred según tarea, stack y señales runtime.
ajustes
Configura Alfred Dev: autonomía, proyecto, Lucius, memoria y personalidad. Antes /alfred-dev:config.
audit
Auditoría completa del proyecto con 4 agentes en paralelo.
discuss
Refina una idea o feature antes de abrir un flujo completo de implementación.