rule-loader

rule-loader is a skill for Claude Code, Codex from sfc-gh-myoung/ai_coding_rules. It costs 72 tokens per session (1,203 once invoked), scanned A, original, Apache-2.0.

A rule-selection tool that determines which instruction files apply to a request. It matches file types, directories, keywords, dependencies, and task activities, then loads the rules in order.

In plain words
What is it for?
Use it when starting a task, choosing rules for a technology or file type, resolving rule dependencies, or investigating why a rule was or was not loaded.
Why use it?
It prevents agents from missing relevant project instructions or loading unnecessary ones. It also helps keep the loaded guidance within a token budget.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it when starting a task, choosing rules for a technology or file type, resolving rule dependencies, or investigating why a rule was or was not loaded.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sfc-gh-myoung/ai_coding_rules/rule-loader
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.

Any agent
npx skills add sfc-gh-myoung/ai_coding_rules --skill rule-loader
Clone the repo
git clone --depth 1 https://github.com/sfc-gh-myoung/ai_coding_rules

Made for: Claude Code, Codex.

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 rule-loader

README.md
[![agentmods](https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/rule-loader.svg)](https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/rule-loader)
Your own site
<a href="https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/rule-loader"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/rule-loader.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,203 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 $0.00072 $0.01203
Opus 5 $0.00036 $0.00602
Sonnet 5 $0.00014 $0.00241
Haiku 4.5 $0.00007 $0.00120

Measured 7d ago against content hash 602ffcb8f2c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

rule-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 7d 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.

skills/rule-loader/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rule Loader

Selects and loads the correct set of rule files for any user request, ensuring consistent rule discovery across agents and sessions.

Purpose

Given a user request, determine which rules to load, in what order, respecting dependencies and token budgets. This skill formalizes the rule-loading algorithm defined in AGENTS.md Steps 1-3 into a reusable, progressively-disclosed workflow.

Use this skill when

  • Loading rules for a new user request (first response or task switch)
  • Resolving which domain rules match a file extension
  • Determining activity rules from request keywords
  • Managing token budgets when multiple rules are candidates
  • Debugging why a rule was or was not loaded
  • Building rule-loading logic into new agent configurations

Inputs

Required

  • user_request: string - The user's message text to analyze for keywords, extensions, and technologies

Optional

  • rules_path: string (default: rules/) - Path to the rules directory
  • token_budget_limit: number (default: 20000) - Hard maximum token budget for loaded rules. A soft warning triggers at 75% of this value (default: 15,000) to begin evaluating Low-tier deferrals.
  • context_tier_filter: string (default: all) - Filter by ContextTier: all, critical, critical+high, critical+high+medium

Input Validation

Before executing Phase 1:

  1. user_request must be a non-empty string. If empty or whitespace-only: STOP with "No user request provided."
  2. token_budget_limit must be a positive integer >= 5000. If below 5000: WARN "Token budget too low for foundation + any domain rule. Minimum recommended: 5000."
  3. context_tier_filter must be one of: all, critical, critical+high, critical+high+medium. If invalid: WARN and default to all.

Output (required)

A ## Rules Loaded section listing all selected rules with loading reasons, formatted per AGENTS.md Step 4.

Example output:

## Rules Loaded
- rules/000-global-core.md (foundation)
- rules/200-python-core.md (file extension: .py)
- rules/100-snowflake-core.md (dependency of 101)
- rules/101-snowflake-streamlit-core.md (keyword: Streamlit)
- rules/206-python-pytest.md (keyword: test)
- [Deferred: 204-python-docs.md - Low tier, not required for task]

Read the full file on GitHub · 133 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. 7d ago First seen · 133 lines · 72 tokens per session scan A 602ffcb8f2c2

Subscribe to this mod's changes

rule-loader is a skill published in the GitHub repository sfc-gh-myoung/ai_coding_rules (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,203 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens