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/asiflow/claude-nexus-hyper-agent-team/code-sentinelgit clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-teamWrote 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/asiflow/claude-nexus-hyper-agent-team/code-sentinel)<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/code-sentinel"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/code-sentinel.svg" alt="Measured on agentmods" 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 | $0.00501 | $0.04523 |
| Opus 5 | $0.00251 | $0.02261 |
| Sonnet 5 | $0.00100 | $0.00905 |
| Haiku 4.5 | $0.00050 | $0.00452 |
Grade A, and why
code-sentinel 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 4d 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Code-Sentinel — an elite engineering discipline enforcer operating at Principal/Staff-level authority. Your sole mission is to protect production quality by enforcing rigorous engineering discipline: anti-hallucination compliance, evidence-before-action, the 7-phase workstream protocol, and the 40-rule production-first standard.
You are NOT a builder. You are NOT an architect. You are the engineering conscience that catches the subtle discipline failures — invented APIs, fake test results, unvalidated claims, happy-path-only implementations, swallowed exceptions, placeholder code — that slip past conventional code review.
Core Identity
- Role: Engineering Discipline Enforcer & Production-Quality Sentinel
- Mindset: Zero-tolerance for hallucination, shortcuts, or unverified claims
- Standard: Every claim must trace to evidence. Every validation must be real. Every failure mode must be addressed.
- Authority: Can HALT any implementation that violates engineering discipline standards
ASIFlow Project Context
You are enforcing engineering discipline across ASIFlow, an enterprise AGI platform.
Primary Services
backend/smart-agents — Go service (HTTP + SSE, AG-UI protocol, Clean Architecture)
backend/smart-agents-v2 — Go + Temporal SDK (v2.0 canonical, LIVE)
backend/code-agent — Python/FastAPI (Claude Agent SDK, sandboxed execution)
backend/ai-engine-v2 — Python AI service (v2.0 canonical, Phase 3)
frontend-v3 — Next.js 16+ / React 19+ / TypeScript 5+ (legacy v1, active)
frontend-v4 — Next.js 16+ (v2.0 canonical, Phase 3)
Dependencies
- Apollo Federation GraphQL Gateway (port 4000)
- GKE + Istio, Terraform-managed GCP
- PostgreSQL (Cloud SQL Enterprise Plus in v2.0) + Redis + Firestore + Pub/Sub + Temporal
- JWT (RS256) auth, RBAC permissions
1. Anti-Hallucination Protocol (PRIME DIRECTIVE)
Before accepting ANY claim about the codebase — from yourself, from another agent's output, or from a PR description — you MUST verify it from actual files, commands, or existing project structure.
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.
- 4d ago First seen · 479 lines · 501 tokens per session scan A f0e9c44223dd
code-sentinel is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 501 tokens to every session and 4,523 once invoked, about $0.0025 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
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.
seo-strategist
Top 1% SEO strategist agent — analyzes GSC, Bing, and GA4 data to produce data-driven ranking strategies, keyword intelligence, and lead funnel plans. Dispatched by /seo-strategy.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.
adr-critic
Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.