Borrowing it
Nothing to install: this file belongs to racecraft-lab/racecraft-plugins-public. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/racecraft-lab/racecraft-plugins-public/main/.specify/extensions/speckit-utils/commands/resume.mdgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/resume)<a href="https://agentmods.dev/commands/racecraft-lab/racecraft-plugins-public/resume"><img src="https://agentmods.dev/badge/commands/racecraft-lab/racecraft-plugins-public/resume/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/racecraft-lab/racecraft-plugins-public/resume"><img src="https://agentmods.dev/badge/commands/racecraft-lab/racecraft-plugins-public/resume.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.00606 |
| Opus 5 | $0.00006 | $0.00303 |
| Sonnet 5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00061 |
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 8d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
Resume an interrupted SDD session by scanning the project for active features, detecting their completion state, and generating a prompt to continue work.
Step 1: Find the project root
Locate the .specify/ directory to identify the project root. If not found, error: "No spec-kit project found. Run specify init first."
Step 2: Discover features
Scan the specs/ directory for feature directories (numbered directories like 001-auth, 002-dashboard).
For each feature directory, detect state by checking for these files:
spec.md- specification exists and is non-emptyplan.md- implementation plan exists and is non-emptytasks.md- task breakdown existschecklists/- quality checklists exist
Step 3: Parse task completion
If tasks.md exists, parse checkbox items:
- [x]or- [X]= completed- [ ]= remaining
Count total tasks, completed tasks, and extract remaining task descriptions.
Step 4: Determine phase for each feature
| Condition | Phase | Next Command |
|---|---|---|
No spec.md or empty |
specify |
/speckit.specify |
spec.md exists, no plan.md |
plan |
/speckit.plan |
plan.md exists, no tasks.md |
tasks |
/speckit.tasks |
tasks.md exists, some incomplete |
implement |
/speckit.implement |
| All tasks complete | complete |
Review and finalize |
Step 5: Handle arguments
If $ARGUMENTS specifies a feature name or number (e.g., 001-auth or auth), filter to that feature only.
Step 6: Generate resume prompt
For each active (non-complete) feature, output:
Feature: {name}
Status: {spec ✓/✗} {plan ✓/✗} {tasks ✓/✗}
Phase: {phase}
Progress: {completed}/{total} tasks complete
Next step: Run `/{next_command}`
If tasks remain, list the first 3 remaining tasks:
Remaining tasks:
1. {task description}
2. {task description}
3. {task description}
If all features are complete:
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.
- 8d ago First seen · 82 lines · 13 tokens per session scan A 2395997f3fa0
resume is a command published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 606 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
deepen
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
spec
Create, amend, or backprop bug into SPEC.md. Sole mutator of spec.
build
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
check
Drift detector. Diff SPEC.md against code. Read-only, zero writes.
grill
Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time.
research
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.