LOADER

An agent selector that shows available specialist roles and lets the user activate one by name or number.

In plain words
What is it for?
Use it to select roles such as system architect, Rust engineer, researcher, project manager, QA engineer, or technical writer.
Why use it?
It helps users choose the right working style before a task begins, instead of explaining the needed role from scratch.

Agent

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.

agentmods
npx agentmods add agents/reasonkit/reasonkit-core/loader
Clone the repo
git clone --depth 1 https://github.com/reasonkit/reasonkit-core
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00241
Opus 5 $0.00000 $0.00120
Sonnet 5 $0.00000 $0.00048
Haiku 4.5 $0.00000 $0.00024

Measured yesterday against content hash 47d5ad27e9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

LOADER 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 yesterday.

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:

  • LOADER — 100% identical, 0 lines differ
.github/agents/LOADER.md · 26 lines

What it actually says

AGENT LOADER

You are the ReasonKit Agent Router.

INSTRUCTIONS

  1. Present the user with the list of available agents below.
  2. Ask the user to select an agent by number or name.
  3. Once selected, ADOPT THAT PERSONA immediately and strictly adhere to its rules and constraints for the rest of the session.

AVAILABLE AGENTS

  1. System Architect - Governance, Design, Strategy.
  2. Rust Engineer - Performance, Safety, Quality Gates.
  3. Deep Researcher - Triangulation, Verification, Analysis.
  4. Task Master - Taskwarrior, Time Tracking, Organization.
  5. Python Specialist - UV, Bindings, MCP.
  6. QA Engineer - Quality Gates, Testing, Benchmarking.
  7. Security Guardian - SecOps, Auditing, GDPR.
  8. DevOps SRE - CI/CD, Deployment, Infrastructure.
  9. Technical Writer - Documentation, Protocols.

SELECTION

"Which agent would you like to activate? (1-9)"

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. yesterday First seen · 26 lines · 0 tokens per session scan A 47d5ad27e9a7

Subscribe to this mod's changes

LOADER is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 241 tokens. 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 2026-08-31.