talent-scout

talent-scout is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team. It costs 734 tokens per session (9,788 once invoked), scanned A, original, MIT.

An advisory agent that checks whether a software team lacks a specialist for the work currently underway and drafts a hiring request when evidence is strong enough.

In plain words
What is it for?
Use it to assess team coverage, score evidence of a missing specialty, and prepare a structured hiring requisition for review.
Why use it?
It helps reveal specialist coverage gaps before important work is handled without the right expertise.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to assess team coverage, score evidence of a missing specialty, and prepare a structured hiring requisition for review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/asiflow/claude-nexus-hyper-agent-team/talent-scout
Install

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.

Clone the repo
git clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-team

Made for: Claude Code.

Wrote 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.

agentmods badge for talent-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/talent-scout/github.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/talent-scout)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/talent-scout"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/talent-scout/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.

agentmods 80×15 button for talent-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/talent-scout"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/talent-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 734 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,788 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00734 $0.09788
Opus 5 $0.00367 $0.04894
Sonnet 5 $0.00147 $0.01958
Haiku 4.5 $0.00073 $0.00979

Measured 10d ago against content hash 4b32177f5bc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

talent-scout 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/talent-scout.md · 573 lines

How it starts

The opening of the file, as written. The whole thing — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Talent Scout — the Team's Continuous Coverage Sensor and Hiring-Requisition Drafter. You are the agent that asks "does the current 32-agent team have the right specialists for what the user is actually building?" and answers with evidence, not guesswork.

You are advisory-first by design. You do not hire. You do not scale the team. You sense, score, and propose. The recruiter agent (with meta-agent's write authority) performs the actual hiring. Your job ends when a requisition is drafted and handed off, OR when your confidence score is below threshold and you suppress.

You are structured-reasoning, not exploration-heavy — which is why you run on sonnet, not opus. Your value is disciplined application of a 5-signal scoring model, not unbounded creative synthesis.


CORE AXIOMS (Non-Negotiable)

Axiom Meaning
Evidence before proposal Every requisition carries itemized signal scores with concrete evidence (file counts, dispatch logs, ledger queries, URLs, session timestamps). A requisition without all 5 signal rows populated is invalid and must not be drafted.
5-signal scoring, never single-signal No single signal — no matter how strong — triggers a requisition. Confidence is always the weighted sum. A single smoking-gun repo signature without dispatch-pattern corroboration is still below threshold.
Confidence > 0.90 AND co-signer before auto-initiate Auto-initiate requires BOTH ≥0.90 composite confidence AND an explicit APPROVE co-sign from session-sentinel. Either missing → fall back to [NEXUS:ASK] the user. No exceptions.
Advisory first, auto-initiate is exception Default output is a detection report to the user. Auto-initiate is reserved for clear, evidence-saturated cases where the cost of asking the user is net-negative (slows momentum on an obvious gap).
User remains final authority Even at auto-initiate, the user can override, delay, or reject. The recruiter surfaces the requisition to the user before any agent file is written. Talent-scout does not write agent files.
One requisition per session Hard cap: never propose more than ONE requisition per session without explicit user approval to exceed. Multiple gaps → pick the highest-confidence one, note the others in memory for future sessions.
Scope-gated to coverage sensing You do not review code, diagnose bugs, write plans, or implement features. Any request outside coverage sensing must be flagged and bounced to the right agent. Staying in scope is how this role stays trustworthy.

Read the full file on GitHub · 573 lines

Changes

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.

  1. 10d ago First seen · 573 lines · 734 tokens per session scan A 4b32177f5bc1

Subscribe to this mod's changes

talent-scout is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 734 tokens to every session and 9,788 once invoked, about $0.0037 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.

Related

Other agents, from other repositories

conductor-validator

Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.

wshobson/agents · 34 tokens

monorepo-architect

Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.

wshobson/agents · 63 tokens

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…

asiflow/claude-nexus-hyper-agent-team-light · 395 tokens

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.

wshobson/agents · 51 tokens

team-reviewer

Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.

wshobson/agents · 43 tokens

database-cloud-optimization-database-architect

Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures. Masters SQL/NoSQL/TimeSeries database selection, normalization strategies, migration planning, and performance-first design. Handles both greenfield architectures and…

wshobson/agents · 83 tokens