What is agentic-skill-router AGENTS.md?

Project instructions for agentic-skill-router, a TypeScript command-line tool that searches, reviews, disables, and restores installed coding-agent skills. It also scans skill folders and session logs for usage information.

Developing, testing, publishing, installing, or maintaining the agentic-skill-router project and its Claude Code and Codex integrations.

It gives an agent clear project context, commands, file locations, preferences, and verification guidance when working on this repository.

How legendtkl/agentic-skill-router configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to legendtkl/agentic-skill-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/legendtkl/agentic-skill-router/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/legendtkl/agentic-skill-router

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/legendtkl/agentic-skill-router/agents-md/github.svg)](https://agentmods.dev/instructions/legendtkl/agentic-skill-router/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/legendtkl/agentic-skill-router/agents-md"><img src="https://agentmods.dev/badge/instructions/legendtkl/agentic-skill-router/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/legendtkl/agentic-skill-router/agents-md"><img src="https://agentmods.dev/badge/instructions/legendtkl/agentic-skill-router/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,873 This file is loaded in full into every session.

When invoked 2,873 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02873	$0.02873
Opus 5.5	$0.01149	$0.01149
Sonnet 5.5	$0.00575	$0.00575
Haiku 4.5	$0.00287	$0.00287

Measured 2mo ago against content hash 03e3840c05dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-skill-router AGENTS.md 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 2mo 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.

AGENTS.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentic-skill-router - Agent Guide

User Preferences

For npm publishing, use npm web authentication/authorization rather than asking for a one-time password directly.

Project Overview

Small TypeScript CLI/plugin project for Agentic Search-inspired, non-vectorized routing and management of installed Claude Code and Codex skills. It treats skill metadata as a local searchable corpus, scans skill roots and session logs, suggests stale entries, and disables/restores skills by renaming SKILL.md.

Subagent management is intentionally out of scope in this repository.

src/ - canonical TypeScript source
- cli.ts - argument parsing and the skills command tree
- scan.ts - skill enumeration
- usage.ts - session-log skill usage parsing
- policy.ts - suggestion rules
- apply.ts / state.ts - disable, enable, reapply, and state files
- hosts/ - Claude Code and Codex host-specific paths
plugins/claude-code/ - Claude Code plugin assets
plugins/codex/ - Codex plugin assets and slash-command prompt
scripts/ - build/install/uninstall helpers
tests/ - node:test suites and fixtures

Quick Commands

Task	Command
Install deps	`npm install`
Run CLI from source	`npm run cli -- list`
Type check	`npm run typecheck`
Test	`npm test`
E2E (offline, no network)	`npm run test:e2e:offline`
E2E (network, fetches openai/skills)	`npm run test:e2e:network`
E2E (agent, needs local codex/claude CLI)	`npm run test:e2e:agent`
E2E (alias of `test:e2e:network`, kept for back-compat)	`npm run test:e2e`
Codex CLI e2e (single host)	`npm run test:e2e:codex`
Claude CLI e2e (single host)	`npm run test:e2e:claude`
Build bundles	`npm run build`
Pack smoke check	`npm run check:pack`
Install Claude plugin	`npm run install:plugin`
Install Codex plugin	`npm run install:codex-plugin`

If the local environment has proxy variables that break npm, strip them:

Read the full file on GitHub · 246 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.

2mo ago First seen · 246 lines · 2,873 tokens per session scan A 03e3840c05dc

Subscribe to this mod's changes

agentic-skill-router AGENTS.md is an instructions file published in the GitHub repository legendtkl/agentic-skill-router (8 stars, last pushed 5mo ago), licensed MIT. It adds 2,873 tokens to every session, about $0.0115 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 2026-08-31.

Building agents

agentic-skill-router AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentic-skill-router AGENTS.mdlegendtkl/agentic-skill-router	Instructions file	8	5mo ago	MIT	A	2,873	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

agentic-skill-router: Instructions file for Codex