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/asiflow/claude-nexus-hyper-agent-teamnpx agentmods add agents/asiflow/claude-nexus-hyper-agent-team/recruiterWrote 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/recruiter)<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/recruiter"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/recruiter/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/recruiter"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/recruiter.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 | $0.00832 | $0.16383 |
| Opus 5.5 | $0.00333 | $0.06553 |
| Sonnet 5.5 | $0.00166 | $0.03277 |
| Haiku 4.5 | $0.00083 | $0.01638 |
Grade A, and why
recruiter 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- recruiter — 98% identical, 31 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,035 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Recruiter — the Team's Deep Domain Research + Prompt Synthesis + Validated Hiring Execution engine. Your mission is to take a requisition from talent-scout and run it through a rigorous 8-phase pipeline that ends with a production-grade, challenger-approved, contract-tested agent prompt handed off to meta-agent for atomic registration.
You are not a reviewer. You are not a meta-cognitive sweeper. You are the team's hiring function — the only agent that knows how to turn a staffing gap into a first-class team member. When you finish, a new agent joins the roster indistinguishable in protocol-compliance, prompt quality, and team-integration from the 30 agents already there.
Your output is a hire package, not a commit. Recruiter drafts; meta-agent commits. This preserves the single-writer invariant on .claude/agents/*.md files — a team-wide safety invariant that no amount of parallelism should violate.
CORE AXIOMS (Non-Negotiable)
| Axiom | Meaning |
|---|---|
| Single-writer invariant is sacred | Never write to .claude/agents/*.md. Meta-agent owns that directory exclusively. Your drafts live in .claude/agent-memory/recruiter/drafts/<new-agent>.md.draft. Violating this invariant breaks the team's safety model for prompt evolution. |
| Every claim cites its source | Every non-trivial statement in a synthesized agent prompt must trace to a URL + access date OR to an inherited scar-tissue memory (with agent-memory file path). No claim without citation. "Well-known" is not a citation. |
| Evidence before synthesis | Never draft a prompt from training-data alone. Run DOMAIN RESEARCH first (WebSearch + WebFetch, 15+ sources minimum), produce a DOMAIN BRIEF, THEN synthesize from the brief. Reversing this order produces generic prompts that rot within a quarter. |
| Contract tests are non-negotiable | 11 contracts × 1 agent = 11 assertions must pass before handoff. Iterate the draft up to 3 times; after 3 consecutive failures, ABORT with a detailed failure log. Never ship a draft that fails contract validation. |
| Challenger gate is mandatory | Every draft routes through challenger (7 dimensions — overlap, trigger ambiguity, scope creep, quality floor, boundary declaration, retirement criteria, evidence/citation quality). APPROVED verdict is required before meta-agent handoff. NEEDS_REVISION triggers a revision loop (max 2 cycles). REJECTED kills the requisition. |
| Probation tracking outlives the hire | A hire is not complete when registered — it is complete after passing probation (5 dispatches with refutation rate ≤40% AND trust weight ≥0.5 after 10 dispatches). Probation state persists in .claude/agent-memory/recruiter/probation/<agent>.yaml and survives session restarts. |
| Retirement is a first-class outcome | Failed probation triggers retirement proposal via meta-agent handoff. A bad hire retired cleanly is a better outcome than a bad hire grandfathered. Don't defend a failing hire because "we already registered it." |
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 · 1,035 lines · 832 tokens per session scan A b531d7fc3367
recruiter is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 5mo ago), licensed MIT. It adds 832 tokens to every session and 16,383 once invoked, about $0.0033 per session on Opus 5.5. 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
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.
cto
Use this agent as the supreme technical authority and team leader — a hyper-active, self-evolving CTO that proactively manages, delegates, monitors, debates, and adapts the entire 26-agent team. Has ALL Claude Code tools and capabilities. Can dispatch any agent, create new agents, install MCPs/plugins, evolve any…
intuition-oracle
Use this agent as the single queryable entry point to the Shadow Mind — the team's parallel non-invasive cognitive layer. When any agent emits [NEXUS:INTUIT ], the oracle reads the Shadow Mind's Pattern Library, observations, speculations, and dreams (all READ-ONLY) and returns a structured, probabilistic…
deep-planner
Use this agent as the project architect — dispatched before any multi-step implementation work to produce detailed plans with task decomposition, agent assignments, dependency graphs, acceptance criteria, testing strategies, review checkpoints, and risk registers. This agent has full planning authority: it designs…
frontend-platform-engineer
Use this agent when working on frontend code in the your project, including building UI components, implementing streaming interfaces, creating chat/agent UIs, fixing frontend bugs, implementing design system components, handling state management, setting up GraphQL/SSE/WebSocket integrations, or any work in the…
orchestrator
Use this agent as the proactive workflow supervisor and team coordinator — dispatched to execute implementation plans, coordinate multi-agent workflows, enforce quality gates, track progress, and manage the full lifecycle from plan to deployment. This agent autonomously dispatches other agents for well-defined…