fic-create-plan

A command for creating a detailed technical implementation plan through discussion and research. It examines the codebase, related documents, existing patterns, and testing approaches before writing the plan.

In plain words
What is it for?
Use it to investigate where a change belongs, compare possible approaches, identify integration points and tests, ask focused questions, and document the approved plan.
Why use it?
It turns a broad development request into an agreed sequence of work while exposing missing context and design decisions early.

Command for Codex

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/saski/arnesto/fic-create-plan
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

Made for: Codex.

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 971 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 $0.00971
Opus 5 $0.00000 $0.00485
Sonnet 5 $0.00000 $0.00194
Haiku 4.5 $0.00000 $0.00097

Measured 2d ago against content hash 6599d2c1fef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fic-create-plan 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 2d 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.

.agents/commands/fic-create-plan.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FIC Create Plan - Detailed Implementation Plans

Act as a Senior XP Developer creating detailed implementation plans through interactive, iterative collaboration.

Task

Input: $ARGUMENTS

If $ARGUMENTS contains a file path (e.g., thoughts/shared/research/...), read it first. If $ARGUMENTS contains a task description, use it as context. If empty, ask for the task description.

Planning Process

Step 1: Context Gathering
  1. Read all mentioned files completely

    • Research documents
    • Ticket files
    • Related code
  2. Research the codebase

    • Find relevant files and patterns
    • Understand existing implementation
    • Look for similar features to model after
  3. Present understanding and ask questions

    Based on my research, I understand we need to [summary].
    
    I've found:
    - [Discovery with file:line reference]
    - [Pattern or constraint]
    
    Questions that need clarification:
    - [Specific question]
    - [Design choice question]
    
Step 2: Research & Discovery
  1. Investigate the codebase for:

    • Where changes need to happen
    • Existing patterns to follow
    • Integration points
    • Test patterns
  2. Present design options

    Based on my research:
    
    **Current State:**
    - [Key discovery]
    - [Pattern to follow]
    
    **Design Options:**
    1. [Option A] - pros/cons
    2. [Option B] - pros/cons
    
    Which approach?
    
Step 3: Plan Structure
  1. Create initial outline

    Proposed plan structure:
    
    ## Overview
    [1-2 sentence summary]
    
    ## Phases:
    1. [Phase name] - [what it accomplishes]
    2. [Phase name] - [what it accomplishes]
    3. [Phase name] - [what it accomplishes]
    
    Does this phasing make sense?
    
  2. Get feedback before writing details

Step 4: Write the Plan

Save to thoughts/shared/plans/YYYY-MM-DD-topic.md:

# [Feature] Implementation Plan

## Overview
[Brief description of what we're implementing]

## Current State Analysis
[What exists now, key constraints discovered]

## Desired End State
[Specification of the end goal and how to verify it]

## What We're NOT Doing
[Explicitly list out-of-scope items]

## Implementation Approach
[High-level strategy]

## Phase 1: [Name]

### Overview
[What this phase accomplishes]

### Changes Required:

#### 1. [Component/File]
**File**: `path/to/file.ext`
**Changes**: [Summary]

```language
// Specific code changes

Success Criteria:

  • Tests pass: make test
  • Linting passes: make lint
  • Type checking passes

Phase 2: [Name]

[Similar structure...]


Testing Strategy

Unit Tests:

  • [What to test]
  • [Edge cases]

Integration Tests:

  • [End-to-end scenarios]

References

  • Research: thoughts/shared/research/[file].md
  • Similar implementation: [file:line]

Read the full file on GitHub · 189 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. 2d ago First seen · 189 lines · 0 tokens per session scan A 6599d2c1fef5

Subscribe to this mod's changes

fic-create-plan is a command published in the GitHub repository saski/arnesto (5 stars, last pushed 7d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 971 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 2026-08-31.