resume

resume is a command for Claude Code from ParkerM2/create-claude-workflow. It costs 22 tokens per session (1,726 once invoked), scanned A, original, MIT.

A recovery command that finds unfinished coding work after a crash, timeout, or closed terminal and identifies where to continue.

In plain words
What is it for?
Use it to inspect progress files, branches, worktrees, and agent-team sessions, then resume an in-progress feature.
Why use it?
It prevents lost progress and helps determine whether a feature is still running, blocked, or complete.

Command for Claude Code

Part of the claude-workflow plugin — 10 skills, 25 commands, 3 agents, 6 hooks 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/parkerm2/create-claude-workflow/resume
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Or install claude-workflow, the plugin that ships this one along with the rest of its 10 skills, 25 commands, 3 agents, 6 hooks.

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 resume

README.md
[![agentmods](https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/resume.svg)](https://agentmods.dev/commands/parkerm2/create-claude-workflow/resume)
Your own site
<a href="https://agentmods.dev/commands/parkerm2/create-claude-workflow/resume"><img src="https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/resume.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,726 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 $0.00022 $0.01726
Opus 5 $0.00011 $0.00863
Sonnet 5 $0.00004 $0.00345
Haiku 4.5 $0.00002 $0.00173

Measured 3d ago against content hash e7f7733d681e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/resume.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/resume — Resume an In-Progress Feature

Invoke this skill to find and resume a previously started (or crashed) feature implementation. Scans progress files, shows status, and picks up where the last session left off.


When to Use

  • Your terminal closed or timed out during /agent-team
  • You want to continue a feature started in a previous session
  • You're unsure if a feature was completed or left in-progress

Phase 1: Scan for In-Progress Features

Scan for in-progress work from both /agent-team sessions (task files) and legacy sessions (JSONL events):

# Check for /agent-team task files (v4 workflow)
ls the progress directory/*/tasks/task-*.md 2>/dev/null

# Check for legacy JSONL event logs
ls the progress directory/*/events.jsonl 2>/dev/null

# Check for active workbranches
git branch --list "work/*"

# Check for feature branches
git branch --list "feature/*"

# Check for existing teams
ls ~/.claude/teams/ 2>/dev/null

# Check for existing worktrees
git worktree list

For /agent-team sessions: if task files exist at .claude/progress/<ticket>/tasks/, read the task files and workflow-state.json to determine state.

For legacy sessions: if events.jsonl exists, read the events to determine state.

If current.md exists, read it for a quick summary. Otherwise, scan events.jsonl to extract:

  • Feature name (from event envelope)
  • Status (check for session.end event — if absent, feature is in-progress)
  • Task counts (count task.completed vs task.started events)
  • Last checkpoint
  • Last event timestamp

Phase 2: Present Options

No progress files found

No in-progress features found in the progress directory.

To start a new feature, run:
  /agent-team "your feature description"

Stop here.

One in-progress feature found

Present a summary and ask to confirm:

Found in-progress feature:

  Feature:      <name>
  Status:       <status>
  Progress:     <N>/<total> tasks complete
  Current Wave: <wave number>
  Last Updated: <timestamp>
  Branch:       feature/<name>

Resume this feature?

Read the full file on GitHub · 249 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 · 249 lines · 22 tokens per session scan A e7f7733d681e

Subscribe to this mod's changes

resume is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,726 once invoked, about $0.0001 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.