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/rahswe/claude-code-full-dev-workflow/resumegit clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflowWhat 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 | $0.00009 | $0.01477 |
| Opus 5 | $0.00005 | $0.00739 |
| Sonnet 5 | $0.00002 | $0.00295 |
| Haiku 4.5 | $0.00001 | $0.00148 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Full-Dev Workflow
You are resuming an interrupted full-dev workflow. Follow these steps to restore context and continue.
Step 1: Check for Existing State
Read the workflow state file at .claude/full-dev.local.md.
If the file does not exist:
- Inform the user: "No interrupted workflow found. Use
/full-dev-workflow:full-dev <feature>to start a new workflow." - Stop here.
Step 2: Parse and Display State Summary
Extract from the state file:
feature: The feature being implementedbranch: The git branchcurrent_phase: Where the workflow was interruptedcompleted_phases: Phases already finisheduser_approved_plan: Whether Phase 0 was approvedmodified_files: Files changed during the workflowtest_status: Current test statuspr_url: PR URL if created
Present a summary to the user:
## Workflow Resume Summary
**Feature**: [feature name]
**Branch**: [branch name]
**Started**: [started_at]
**Last Updated**: [updated_at]
### Progress
- Completed Phases: [list]
- Current Phase: [current_phase] ([phase_name])
- Plan Approved: [yes/no]
### Test Status
- Status: [passing/failing]
- Pass: [count] | Fail: [count]
- Last Run: [timestamp]
### Modified Files
[list of files]
### PR Status
[PR URL if exists, or "Not created yet"]
Step 3: Validate State Integrity
Perform validation checks:
- Git branch matches:
git branch --show-currentshould match state branch - Plan file exists: If
plan_fileis set, verify it exists - PR exists (if in Phase 9-10): Verify PR URL is valid with
gh pr view - Phase completion signals worked:
completed_phasesshould contain phases 0 through (current_phase- 1)- If gaps exist (e.g.,
current_phase: 5butcompleted_phases: []), warn user about potentially skipped phases - Suggest using
git diff --name-onlyto verify actual work done vs. state tracking
State Recovery (if phase tracking is out of sync):
If you detect that phases were completed but not tracked (state shows phase 0 but files clearly show implementation):
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.
- 2d ago First seen · 197 lines · 9 tokens per session scan A f885dc639334
resume is a command published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 1,477 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.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.