codebase-conformity

codebase-conformity is a skill for Claude Code from boparaiamrit/skills-by-amrit. It costs 69 tokens per session (3,459 once invoked), scanned A, original, MIT.

A workflow for matching new code to the patterns already used in an existing codebase.

In plain words
What is it for?
It is for adding components, pages, routes, endpoints, functions, utilities, and other changes to an established project.
Why use it?
It prevents new files and features from introducing inconsistent naming, structure, error handling, or data flow.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit It is for adding components, pages, routes, endpoints, functions, utilities, and other changes to an established project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/boparaiamrit/skills-by-amrit/codebase-conformity
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 codebase-conformity
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 codebase-conformity

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/codebase-conformity"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/codebase-conformity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,459 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 $0.00069 $0.03459
Opus 5 $0.00034 $0.01729
Sonnet 5 $0.00014 $0.00692
Haiku 4.5 $0.00007 $0.00346

Measured 8d ago against content hash 6e01cadbd8f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

codebase-conformity 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 8d 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/codebase-conformity/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Conformity

Overview

AI assistants "innovate" when they should conform. They introduce new patterns, rename conventions, restructure layouts, and use different error handling — all in the same codebase. This skill forces the AI to read before writing, match before creating, and verify before claiming done.

Core principle: The existing codebase is the specification. Read it. Match it. Don't improve it in the same commit.

The Iron Law

EVERY NEW FILE, FUNCTION, AND FEATURE MUST CONFORM TO EXISTING CODEBASE PATTERNS. NO EXCEPTIONS. NO INNOVATIONS. NO "BETTER WAYS."

When to Use

Mandatory (always active):

  • Adding a new file, component, page, route, or endpoint
  • Adding a new function, hook, service, or utility
  • Modifying existing code as part of a feature
  • After any AI-generated code (including your own)
  • Implementing any task from a plan

Recommended:

  • Before reviewing code (check conformity first)
  • After a refactoring (verify patterns held)
  • When onboarding to an existing codebase

When NOT to Use

  • Greenfield projects with no existing code (there's nothing to conform TO)
  • When explicitly refactoring patterns to a NEW standard (use refactoring-safely)
  • When migrating architecture (use writing-plansexecuting-plans)
  • When the existing pattern IS the bug (fix the pattern separately, then conform)

Anti-Shortcut Rules

YOU CANNOT:
- Write code before reading at least 3 sibling files in the same directory — you don't know the pattern yet
- Introduce a new library, utility, or abstraction that doesn't already exist in the codebase — conform, don't innovate
- Use a different naming convention than the existing files — even if you prefer it
- Use a different error handling pattern than existing code — consistency > elegance
- Use a different import style or order than existing files — match them exactly
- Use a different component structure than existing components — structure is a pattern too
- Say "this is a common best practice" to justify deviating — the codebase's practice is the only practice
- Claim conformity without side-by-side comparison — "it looks right" is not verification
- Change an existing pattern while adding a feature — one concern per commit
- Skip double verification — context window amnesia is real, verify twice

Read the full file on GitHub · 339 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. 8d ago First seen · 339 lines · 69 tokens per session scan A 6e01cadbd8f3

Subscribe to this mod's changes

codebase-conformity is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 3,459 once invoked, about $0.0003 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 2026-09-03.