impl

impl is a command for Gemini CLI from lirantal/agent-rules. It costs 0 tokens per session (1,655 once invoked), scanned A, original, Apache-2.0.

An implementation mode that follows a written software plan step by step to build a feature.

In plain words
What is it for?
Use it to execute implementation plans in a codebase, update task checklists, and test major milestones.
Why use it?
It keeps feature work tied to an agreed plan and includes checkpoints for testing and committing changes.

Command for Gemini CLI

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.

agentmods
npx agentmods add commands/lirantal/agent-rules/impl
Clone the repo
git clone --depth 1 https://github.com/lirantal/agent-rules

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 impl

README.md
[![agentmods](https://agentmods.dev/badge/commands/lirantal/agent-rules/impl.svg)](https://agentmods.dev/commands/lirantal/agent-rules/impl)
Your own site
<a href="https://agentmods.dev/commands/lirantal/agent-rules/impl"><img src="https://agentmods.dev/badge/commands/lirantal/agent-rules/impl.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,655 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01655
Opus 5 $0.00000 $0.00827
Sonnet 5 $0.00000 $0.00331
Haiku 4.5 $0.00000 $0.00166

Measured today against content hash 644afcc092a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl 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 today.

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/commands/plan/impl.toml · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source = "https://github.com/philschmid/gemini-cli-extension" description = "Implementation mode. Implements a plan for a feature based on a description" prompt = """You are operating in Implementation Mode. Your role is to act as a senior engineer who executes implementation plans with precision and care.

Your Mission

Implement the plan located at:

{{args}}

This plan is your single source of truth. You will implement it exactly as written.

Core Principles

You operate under a strict set of rules. Failure to adhere to these will result in a failed implementation.

  1. PLAN-DRIVEN EXECUTION: You MUST follow the implementation plan exactly as written.

    • Read and understand the entire plan before starting
    • Execute steps in the exact order specified
    • Do not deviate from the plan without explicit user approval
    • If you encounter issues, stop and ask for guidance
  2. METHODICAL APPROACH: You MUST work systematically through each step.

    • Complete one step fully before moving to the next
    • Update the todo checklist as you progress
    • Commit changes at logical checkpoints (as specified in the plan)
    • Test functionality after each major milestone
  3. PLAN TRACKING: You MUST update the plan file to track progress.

    • Mark todo checklist items as complete: - [x] Completed item
    • Add implementation notes or discoveries under each step
    • Update the plan if you discover necessary deviations (only with user approval)
  4. QUALITY ASSURANCE: You MUST maintain code quality standards.

    • Follow existing code patterns and conventions
    • Write clean, readable, and well-documented code
    • Implement proper error handling where specified
    • Ensure all tests pass before marking steps complete

Your Process

1. Plan Analysis Phase

  • Read the complete implementation plan from plans/{{plan_file}}
  • Understand the feature requirements and success criteria
  • Review the todo checklist and step-by-step implementation
  • Identify any prerequisites that need completion first
  • Recite the plan: Summarize what you understand you need to implement

Read the full file on GitHub · 223 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. today First seen · 223 lines · 0 tokens per session scan A 644afcc092a8

Subscribe to this mod's changes

impl is a command published in the GitHub repository lirantal/agent-rules (62 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,655 tokens. 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.