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.
npx skills add boparaiamrit/skills-by-amrit --skill codebase-conformitygit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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.
[](https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/codebase-conformity)<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.
<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>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 | $0.00069 | $0.03459 |
| Opus 5 | $0.00034 | $0.01729 |
| Sonnet 5 | $0.00014 | $0.00692 |
| Haiku 4.5 | $0.00007 | $0.00346 |
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.
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-plans→executing-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
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.
- 8d ago First seen · 339 lines · 69 tokens per session scan A 6e01cadbd8f3
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…