mega-resume

A command for continuing an interrupted mega-plan, a large multi-step development plan. It checks saved plan files and worktrees to find the current progress before resuming.

In plain words
What is it for?
Use it to resume plan-cascade execution, inspect the current plan status, and continue unfinished work from the detected state.
Why use it?
It removes the need to reconstruct manually which steps were finished after an interruption. It supports both newer and older locations for the saved plan data.

Command

Part of the plan-cascade plugin — 7 skills, 33 commands 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/taoidle/plan-cascade/mega-resume
Clone the repo
git clone --depth 1 https://github.com/Taoidle/plan-cascade

Or install plan-cascade, the plugin that ships this one along with the rest of its 7 skills, 33 commands.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,081 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 $0.00034 $0.04081
Opus 5 $0.00017 $0.02041
Sonnet 5 $0.00007 $0.00816
Haiku 4.5 $0.00003 $0.00408

Measured 3d ago against content hash 8a802f55b0d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mega-resume 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 3d 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.

commands/mega-resume.md · 547 lines

How it starts

The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume Interrupted Mega Plan

Resume execution of an interrupted mega-plan by detecting the current state from existing files.

Path Storage Modes

This command works with both new and legacy path storage modes:

New Mode (Default)

Files are stored in user data directory:

  • Windows: %APPDATA%/plan-cascade/<project-id>/
  • Unix/macOS: ~/.plan-cascade/<project-id>/

File locations:

  • mega-plan.json: <user-dir>/mega-plan.json
  • .mega-status.json: <user-dir>/.state/.mega-status.json
  • Worktrees: <user-dir>/.worktree/<feature-name>/

Legacy Mode

All files in project root:

  • mega-plan.json: <project-root>/mega-plan.json
  • .mega-status.json: <project-root>/.mega-status.json
  • Worktrees: <project-root>/.worktree/<feature-name>/

The command auto-detects which mode is active and scans the appropriate directories.

Tool Usage Policy (CRITICAL)

To avoid command confirmation prompts during automatic execution:

  1. Use Read tool for file reading - NEVER use cat via Bash

    • Read("mega-plan.json"), Read(".mega-status.json"), Read(".worktree/x/progress.txt")
    • Bash("cat mega-plan.json")
  2. Use Glob tool for finding files - NEVER use ls or find via Bash

    • Glob(".worktree/*/prd.json")
    • Bash("ls .worktree/")
  3. Use Grep tool for content search - NEVER use grep via Bash

    • Grep("[PRD_COMPLETE]", path=".worktree/x/progress.txt")
    • Bash("grep '[PRD_COMPLETE]' ...")
  4. Only use Bash for actual system commands:

    • Git operations: git worktree add, git merge
    • Directory creation: mkdir -p
    • File writing: echo "..." >> progress.txt

Compatibility: Works with both old-style (pre-4.1.1) and new-style mega-plan executions.

Arguments

  • --auto-prd: Continue in fully automatic mode (no manual intervention)

Step 1: Verify Mega Plan Exists

# Get mega-plan path from PathResolver
MEGA_PLAN_PATH=$(uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; print(PathResolver(Path.cwd()).get_mega_plan_path())" 2>/dev/null || echo "mega-plan.json")

if [ ! -f "$MEGA_PLAN_PATH" ]; then
    echo "============================================"
    echo "ERROR: No mega-plan.json found"
    echo "============================================"
    echo "Searched at: $MEGA_PLAN_PATH"
    echo "Nothing to resume."
    echo "Use /plan-cascade:mega-plan <description> to create a new plan."
    exit 1
fi

Read the full file on GitHub · 547 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. 3d ago First seen · 547 lines · 34 tokens per session scan A 8a802f55b0d2

Subscribe to this mod's changes

mega-resume is a command published in the GitHub repository Taoidle/plan-cascade (131 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 4,081 once invoked, about $0.0002 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 2026-08-30.