Home / akillness / jeo-skills · .agent-skills/agent-tool-routing/SKILL.md · GitHub

agent-tool-routing skillA

agent-tool-routing is agent-read markdown (skill) from akillness/jeo-skills: Tool registry, capability discovery, schema-first routing, router policies and fallbacks. Use when an agent has more than ~15 tools, multiple MCP servers, or needs dynamic tool selection based on context..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Agent Tool Routing

## Overview

Past ~15 tools, the LLM's tool-selection accuracy collapses. The fix is a **router layer**: discover capabilities, narrow the tool set per turn, then hand a small focused set to the LLM. This skill builds that router.

## When to use

- Agent has 20+ tools and picks the wrong one
- Multiple MCP servers — too many overlapping tools
- Tools come and go at runtime (per-tenant, per-permission)
- Need fallback chains (preferred tool → cheaper tool → cached)
- Cost: every unused tool description wastes input tokens

## Architecture

```
Request → [Capability Discovery] → [Router] → [Top-K Tools] → LLM
                  ↑                    ↑
            registry index      semantic + policy
```

## Tool registry

```python
@dataclass
class ToolEntry:
    name: str
    description: str           # LLM-facing
    schema: dict               # JSON Schema
    embedding: list[float]     # for semantic match
    tags: set[str]             # billing, read, write, hitl
    cost_usd_per_call: float
    p95_latency_ms: int
    requires_scopes: set[str]
    fallback: str | None       # tool name to try if this fails
```
…

Read the whole file at its exact version.

How to install

Latest version
mdr add akillness/jeo-skills/agent-tool-routing@git:20260920.2a2b733
Exact content
mdr add akillness/jeo-skills/agent-tool-routing@sha256:bdbe4fe3991bc5f7

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4bytt67tfgtqrpmg.svg)](https://markdownregistry.com/a/art_4bytt67tfgtqrpmg)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260920.2a2b733 latest2026-09-20 2a2b733 3,828 BA view · diff
git:20260919.9f2a9082026-09-19 9f2a908 3,834 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3828 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

akillness/jeo-skills · 47 stars · license none · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4bytt67tfgtqrpmg
GET https://markdownregistry.com/api/v1/resolve?ref=akillness/jeo-skills/agent-tool-routing
GET https://markdownregistry.com/api/v1/blob/bdbe4fe3991bc5f7eba9d77ea6a7aee8ee6d49ed59e65f35b0f13275114c14a7

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from akillness/jeo-skills

a2a-protocol skill
akillness/jeo-skills · .agent-skills/a2a-protocol/SKILL.md · Agent-to-Agent horizontal messaging — Linux Foundation AAIF 2026 standard. Use when multiple agents across…
git:20260920.2a2b733 · audit A · 47 stars
ab-test-analysis skill
akillness/jeo-skills · .agent-skills/ab-test-analysis/SKILL.md · Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and…
git:20260919.9f2a908 · audit A · 47 stars
academic-research skill
akillness/jeo-skills · .agent-skills/academic-research/SKILL.md · Full academic research pipeline from discovery to publication — 4 reference pipelines, 27 modes, 39-agent ensemble…
v1.0.0 · audit A · 47 stars
agent-benchmarking skill
akillness/jeo-skills · .agent-skills/agent-benchmarking/SKILL.md · Map agent capabilities to standard benchmarks (SWE-bench, WebArena, OSWorld, GAIA, TauBench) plus custom regression…
git:20260919.9f2a908 · audit A · 47 stars
agent-guardrails skill
akillness/jeo-skills · .agent-skills/agent-guardrails/SKILL.md · Layered agent safety — prompt-injection defense, data exfiltration prevention, tool-misuse blocking via NeMo Guardrails…
git:20260919.9f2a908 · audit B · 47 stars
agent-manager skill
akillness/jeo-skills · .agent-skills/agent-manager/SKILL.md · tmux + Python agent lifecycle manager — start, stop, monitor, and assign tasks to AI agents running in tmux sessions…
v1.0 · audit A · 47 stars
agent-memory-architecture skill
akillness/jeo-skills · .agent-skills/agent-memory-architecture/SKILL.md · Design tiered agent memory — core / recall / archival — with backend selection (mem0, Letta, Zep/Graphiti, LangMem) and…
git:20260919.9f2a908 · audit A · 47 stars
agent-observability skill
akillness/jeo-skills · .agent-skills/agent-observability/SKILL.md · Instrument LLM agents with traces, metrics, and replay. Use when an agent in production is silently failing…
git:20260919.9f2a908 · audit A · 47 stars
agent-principles skill
akillness/jeo-skills · .agent-skills/agent-principles/SKILL.md · Core principles for collaborative development with AI agents. Defines divide-and-conquer, context management…
v2.0.0 · audit A · 47 stars
agent-pulse skill
akillness/jeo-skills · .agent-skills/agent-pulse/SKILL.md · Operate and extend barretlee/agent-pulse, the evidence-backed AI industry intelligence system: inspect source catalog…
v1.0 · audit A · 47 stars
agent-reach skill
akillness/jeo-skills · .agent-skills/agent-reach/SKILL.md · Operate Panniantong/Agent-Reach, the MIT-licensed installer, doctor, and routing layer for platform-specific internet…
v1.0.0 · audit A · 47 stars
agent-system-design skill
akillness/jeo-skills · .agent-skills/agent-system-design/SKILL.md · Production agent SLA discipline — MAX_LOOPS, MAX_TOKENS, MAX_COST, MAX_LATENCY, MAX_TOOL_CALLS, circuit breakers…
git:20260920.2a2b733 · audit A · 47 stars

Every file in akillness/jeo-skills

Browse by kind, by grade A, or by owner.