skills-by-amrit: Instructions file for Gemini CLI

GEMINI.md

skills-by-amrit GEMINI.md is an instructions file for Gemini CLI from boparaiamrit/skills-by-amrit. It costs 3,935 tokens per session, scanned A, original, MIT.

A set of instructions for using reusable skills in an AI-assisted software-development workflow, with rules for planning, evidence, debugging, reviews, and audits.

In plain words
What is it for?
Use it to structure development work, activate the right skill for a feature or bug, investigate problems before fixing them, and verify results before calling work complete.
Why use it?
It helps an AI assistant choose relevant procedures and avoid making unsupported claims or changing code before understanding the task.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is boparaiamrit/skills-by-amrit's own configuration. It tells Gemini CLI how to work on skills-by-amrit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills-by-amrit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to boparaiamrit/skills-by-amrit. 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/boparaiamrit/skills-by-amrit/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

Made for: Gemini CLI.

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 skills-by-amrit GEMINI.md

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

agentmods 80×15 button for skills-by-amrit GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/boparaiamrit/skills-by-amrit/gemini-md"><img src="https://agentmods.dev/badge/instructions/boparaiamrit/skills-by-amrit/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,935 This file is loaded in full into every session.
When invoked 3,935 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03935 $0.03935
Opus 5 $0.01968 $0.01968
Sonnet 5 $0.00787 $0.00787
Haiku 4.5 $0.00394 $0.00394

Measured 11d ago against content hash 87c08e23bb1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skills-by-amrit GEMINI.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 11d 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.

GEMINI.md · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills by Amrit

v4.0.0 — An agentic skills framework for software development that makes AI assistants think like senior staff engineers.

How It Works

You have a library of composable skills installed in .agent/skills/. Before any task, check if a relevant skill exists. Skills are not suggestions — they are mandatory workflows when their activation conditions are met.

Check skills before:

  • Writing any code
  • Debugging any issue
  • Reviewing any PR
  • Auditing any system
  • Planning any feature
  • Refactoring any module

Core Principles

Read and internalize rules/core-principles.md before any work.

The four non-negotiables:

  1. Evidence before claims — Never say "done" without verification
  2. Root cause before fixes — Never patch symptoms
  3. Plan before code — Never start coding without understanding what you're building
  4. Context before degradation — Quality drops as context fills. Plan for it.

Skill Activation

Skills activate automatically when their conditions are met. You MUST use the relevant skill — skipping is not an option.

Situation Required Skill
New feature request brainstorming/discusswriting-plansexecuting-plans
Bug report systematic-debugging
"Audit this codebase" codebase-mappingarchitecture-audit
"Is this secure?" security-audit
"Why is this slow?" performance-audit
"Review this code" code-review
Writing tests test-driven-development
About to say "done" verification-before-completion
Changing existing code refactoring-safely
Database questions database-audit
Frontend issues frontend-audit
API design api-design-audit
Deployment concerns ci-cd-audit
Accessibility accessibility-audit
Logging/monitoring observability-audit
Dependency updates dependency-audit
Production incident incident-response
Writing docs writing-documentation
Git operations git-workflow
API integration full-stack-api-integration
Completeness check product-completeness-audit
Deep audit brutal-exhaustive-audit
Cross-session memory persistent-memory
Complex multi-step task / LLM Council agent-team-coordination
Multi-agent team task agent-team-coordination (uses real subagent spawning)
Adding code to existing codebase codebase-conformity
Creating new skills writing-skills
Discovering skills using-skills
Pre-planning decisions /discuss command
Configuration management /settings command
Verification gaps found /gap-closure workflow

Read the full file on GitHub · 421 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. 11d ago First seen · 421 lines · 3,935 tokens per session scan A 87c08e23bb1b

Subscribe to this mod's changes

skills-by-amrit GEMINI.md is an instructions file published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 3,935 tokens to every session, about $0.0197 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens