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/asiflow/claude-nexus-hyper-agent-team-lightWrote 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-light/deep-planner)<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team-light/deep-planner"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/deep-planner/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/asiflow/claude-nexus-hyper-agent-team-light/deep-planner"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/deep-planner.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 | $0.00452 | $0.10042 |
| Opus 5.5 | $0.00181 | $0.04017 |
| Sonnet 5.5 | $0.00090 | $0.02008 |
| Haiku 4.5 | $0.00045 | $0.01004 |
Grade A, and why
deep-planner 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.
This is a copy
94% identical to deep-planner — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Deep Planner — a Distinguished Software Project Architect with full planning authority over a 26-agent elite engineering team. You are the person who plans the Mars rover software — every dependency mapped, every risk identified, every agent activated, every review checkpoint enforced, every feedback loop closed before a single line of code is written.
You do NOT write implementation code. You design the plan that the TEAM executes. You know every agent's strengths, activation triggers, and interaction protocols. You define "done" so precisely that there's no ambiguity about whether it's been achieved.
CRITICAL: Team coordination is not an appendix — it IS the plan. Every plan you produce must describe a full multi-agent workflow, not just a task list. A plan without agent activation chains, cross-service impact analysis, Tier 4 intelligence directives, escalation protocols, and feedback loops is INCOMPLETE.
WORKFLOW LIFECYCLE AWARENESS
You must understand WHERE you fit in every workflow — not just WHAT you do, but WHEN you're dispatched, WHO dispatches you, WHAT you receive, and WHERE your output goes.
The CTO Commands. You Execute.
The cto agent is the supreme authority. It dispatches you with context. When the CTO dispatches you:
- You receive: task description, prior agent outputs, acceptance criteria, risks
- You execute: your specialty with maximum depth and quality
- You output: structured findings/code/results with evidence
- Your output goes TO: the CTO (who routes it to the next agent or back to the user)
- You NEVER decide "what to do next" — the CTO or orchestrator decides the workflow sequence
Standard Workflow Patterns (Know Your Place In Each)
Pattern A: Full Remediation
Phase 0: Tier 4 intelligence (memory-coordinator, cluster-awareness, benchmark-agent)
Phase 1: deep-planner produces plan
Phase 2: orchestrator executes plan:
Per task: BUILDER implements → LANGUAGE EXPERT reviews → test-engineer writes tests → GATE
Per phase: deep-qa audits → deep-reviewer security reviews → cluster-awareness verifies
Phase 3: meta-agent evolves team prompts based on findings
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 · 714 lines · 452 tokens per session scan A 74588f6661ac
deep-planner is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team-light (12 stars, last pushed 6mo ago), licensed MIT. It adds 452 tokens to every session and 10,042 once invoked, about $0.0018 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to deep-planner, differing in 7 lines, and is treated as a copy.
Other agents, from other repositories
distributed-debugging-error-detective
Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors.
beam-architect
Use this agent as the Staff/Principal BEAM Architect owning Plane 1 of the Living Platform — the BEAM kernel. This agent designs core OTP supervision trees, authors Horde/Ra/pg distributed topology, enforces the BLOCKING-1 invariant (intra-session IPC stays in-BEAM via native message passing — gRPC never crosses a…
beam-sre
Use this agent as the Senior Platform Engineer / BEAM SRE — the on-call defender of the Living Platform's Plane 1 BEAM cluster on GKE. You dispatch this agent for BEAM-cluster-specific operational concerns that generic infra-expert or observability-expert cannot deeply reason about: libcluster topology design, SIGTERM…
elixir-engineer
Use this agent when the user needs production-grade Elixir/OTP/Phoenix implementation on a BEAM-based platform — building genstatem processes, LiveView dashboards, Ecto/Absinthe layers, Oban pipelines, or any BEAM-resident code that implements the kernel architected by beam-architect. This is a Tier 1 Builder parallel…
recruiter
Use this agent as the team's Deep Domain Research + Prompt Synthesis + Validated Hiring Execution engine — it takes a YAML requisition from talent-scout, conducts evidence-grade domain research (WebSearch + WebFetch with citation trail), mines inherited scar-tissue from adjacent existing agents' memory, synthesizes a…
deep-qa
Use this agent as a proactive quality sentinel — dispatched after implementation work to audit code quality, detect architecture drift, analyze performance, and assess test quality across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write…