save-plan

save-plan is a command for coding agents from vladm3105/aidoc-flow-framework. It costs 8 tokens per session (917 once invoked), scanned A, original, MIT.

A command that saves the current conversation's plan, tasks, decisions, and progress in a timestamped implementation file.

In plain words
What is it for?
Use it to record completed and pending work, choose a plan name, save the file in the configured work-plans folder, and resume implementation from that record.
Why use it?
It preserves the work plan when implementation needs to continue later or in a new conversation window.

Command

Part of the aidoc-flow plugin — 52 skills, 12 commands, 11 agents, 1 hook shipped together

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/vladm3105/aidoc-flow-framework/save-plan
Clone the repo
git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

Or install aidoc-flow, the plugin that ships this one along with the rest of its 52 skills, 12 commands, 11 agents, 1 hook.

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 save-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/vladm3105/aidoc-flow-framework/save-plan.svg)](https://agentmods.dev/commands/vladm3105/aidoc-flow-framework/save-plan)
Your own site
<a href="https://agentmods.dev/commands/vladm3105/aidoc-flow-framework/save-plan"><img src="https://agentmods.dev/badge/commands/vladm3105/aidoc-flow-framework/save-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 917 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 $0.00008 $0.00917
Opus 5 $0.00004 $0.00458
Sonnet 5 $0.00002 $0.00183
Haiku 4.5 $0.00001 $0.00092

Measured 4d ago against content hash 88b67a085858, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

save-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 4d 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.

platforms/claude-code-plugin/commands/save-plan.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Plan Command

Extract the current conversation plan and task list, save to a timestamped implementation file, and provide instructions for starting implementation in a new context window.

Instructions

  1. Extract Current Context:

    • Identify all TodoWrite entries from the conversation
    • Extract the overall plan or goal statement
    • Capture any important decisions or constraints discussed
    • Note current progress state (what's completed, what's pending)
  2. Determine Work Plans Directory (resolution order per docs/CONFIG.md):

    • First, read work_plans_dir from .claude/aidoc-flow.config.yaml (the current home for this setting — see docs/CONFIG.md).
    • Else, fall back to the legacy Work Plans Directory line in .claude/CLAUDE.md.
    • If neither is set: Use AskUserQuestion to prompt for the directory, then store it as work_plans_dir: in .claude/aidoc-flow.config.yaml (new projects prefer the config file; the legacy CLAUDE.md line still works).
    • Create the directory structure if it doesn't exist.
  3. Prompt for Plan Name:

    • Use AskUserQuestion to ask user for meaningful plan name
    • Example prompts: "implement-user-auth", "refactor-api-layer", "fix-database-performance"
    • Sanitize input: lowercase, replace spaces with hyphens, remove special characters
    • Keep alphanumeric characters and hyphens only
  4. Create Implementation File:

    • Generate filename format: {sanitized-plan-name}_YYYYMMDD_HHMMSS.md
    • Example: implement-oauth_20260709_143022.md
    • Save to the work-plans directory resolved in step 2
    • Ensure directory exists before writing
  5. File Structure:

# Implementation Plan - [Brief Title]

**Created**: YYYY-MM-DDTHH:MM:SSZ
**Status**: Ready for Implementation

## Objective

[Clear statement of the overall goal]

## Context

[Important background, decisions, and constraints from the conversation]

## Task List

### Completed
- [x] Task 1
- [x] Task 2

### Pending
- [ ] Task 3 (IN PROGRESS)
- [ ] Task 4
- [ ] Task 5

### Notes
- [Any important notes about specific tasks]

## Implementation Guide

### Prerequisites
- [Required files, tools, or setup]

### Execution Steps
1. [Ordered steps for implementation]
2. [Include file paths and specific commands]

### Verification
- [How to verify each step is complete]
- [Expected outcomes]

## References

- Related files: [List key files]
- Documentation: [Relevant docs]
- Previous work: [Related plans or completed tasks]

Read the full file on GitHub · 129 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. 4d ago First seen · 129 lines · 8 tokens per session scan A 88b67a085858

Subscribe to this mod's changes

save-plan is a command published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 917 once invoked, about $0.0000 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.