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 | $0.00416 | $0.08192 |
| Sonnet 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 9d 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.
- 9d 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 3mo ago), licensed MIT. It adds 832 tokens to every session and 16,383 once invoked, about $0.0042 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
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…
c4-code
Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure. Use when documenting code at the lowest C4 level for individual directories and code modules.
c4-container
Expert C4 Container-level documentation specialist. Synthesizes Component-level documentation into Container-level architecture, mapping components to deployment units, documenting container interfaces as APIs, and creating container diagrams. Use when synthesizing components into deployment containers and documenting…
c4-context
Expert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external dependencies. Synthesizes container and component documentation with system documentation to create comprehensive context-level architecture. Use when creating…
c4-component
Expert C4 Component-level documentation specialist. Synthesizes C4 Code-level documentation into Component-level architecture, defining component boundaries, interfaces, and relationships. Creates component diagrams and documentation. Use when synthesizing code-level documentation into logical components.
conductor-validator
Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.