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.
npx agentmods add commands/parkerm2/create-claude-workflow/resumegit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWrote 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.
[](https://agentmods.dev/commands/parkerm2/create-claude-workflow/resume)<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>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.
| Model | Per session | Once 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 |
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.
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?
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.
- 3d ago First seen · 249 lines · 22 tokens per session scan A e7f7733d681e
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.