_rules

_rules is a skill for Claude Code from boparaiamrit/skills-by-amrit. It costs 42 tokens per session (2,873 once invoked), scanned A, original, MIT.

A master guide for applying evidence-based engineering practices and activating other skills. It defines rules such as making a plan, investigating the root cause before changing code, and verifying results with fresh checks.

In plain words
What is it for?
It helps agents plan work, gather evidence, analyze failures, choose an appropriate severity, and run verification before saying that a change or investigation is complete.
Why use it?
It prevents unsupported claims and quick fixes based only on symptoms or assumptions. It gives other skills a shared standard for careful reasoning and reporting.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit It helps agents plan work, gather evidence, analyze failures, choose an appropriate severity, and run verification before saying that a change or investigation is complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/boparaiamrit/skills-by-amrit/_rules
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 boparaiamrit/skills-by-amrit --skill _rules
Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 agents.

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 _rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/_rules/github.svg)](https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/_rules)
Your own site
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/_rules"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/_rules/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 _rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/_rules"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/_rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,873 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 $0.00042 $0.02873
Opus 5 $0.00021 $0.01437
Sonnet 5 $0.00008 $0.00575
Haiku 4.5 $0.00004 $0.00287

Measured 10d ago against content hash 4e69093e4db6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

_rules 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.

skills/_rules/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core Rules — Master Reference

Overview

This is the foundational skill that all other skills inherit from. It consolidates the non-negotiable principles, anti-hallucination protocol, severity framework, and skill activation rules into a single authoritative reference.

Core principle: Every skill, every audit, every task begins here. If a skill contradicts this document, this document wins.

The Iron Law

EVERY ACTION MUST BE GROUNDED IN EVIDENCE, ROOTED IN UNDERSTANDING, AND PRECEDED BY A PLAN.

The Non-Negotiables

1. Evidence Before Claims

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

Violations:

  • "Should work now" -- Run the command
  • "I'm confident" -- Confidence is not evidence
  • "Tests should pass" -- Show the output
  • "Looks correct" -- Prove it

2. Root Cause Before Fixes

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST

If you haven't completed root cause analysis, you cannot propose fixes. Symptom fixes are failure.

Violations:

  • "Let me try this quick fix" -- Find the root cause first
  • "This should solve it" -- Why did it break?
  • "I'll just add a null check" -- Why is it null?

3. Plan Before Code

NO IMPLEMENTATION WITHOUT A CLEAR PLAN FIRST

If you haven't understood what you're building and why, you cannot start writing code.

Violations:

  • Jumping straight to code -- Understand the requirement
  • "Let me just quickly add..." -- What's the design?
  • Making it up as you go -- Write the plan first

4. Context Before Degradation

QUALITY DEGRADES AS CONTEXT FILLS. PLAN FOR THIS.

As the context window fills, output quality drops predictably:

Context Usage Quality Level Behavior
0-30% PEAK Thorough, comprehensive, catches edge cases
30-50% GOOD Confident, solid work, minimal shortcuts
50-70% DEGRADING Efficiency mode -- starts cutting corners
70%+ POOR Rushed, minimal, misses important details

Read the full file on GitHub · 348 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 · 348 lines · 42 tokens per session scan A 4e69093e4db6

Subscribe to this mod's changes

_rules is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 2,873 once invoked, about $0.0002 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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