Borrowing it
Nothing to install: this file belongs to Black-coffe/vulyk. 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/Black-coffe/vulyk/main/.claude/commands/vulyk-resume.mdgit clone --depth 1 https://github.com/Black-coffe/vulykWrote 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/black-coffe/vulyk/vulyk-resume)<a href="https://agentmods.dev/commands/black-coffe/vulyk/vulyk-resume"><img src="https://agentmods.dev/badge/commands/black-coffe/vulyk/vulyk-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/black-coffe/vulyk/vulyk-resume"><img src="https://agentmods.dev/badge/commands/black-coffe/vulyk/vulyk-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 | $0.00017 | $0.00440 |
| Opus 5.5 | $0.00007 | $0.00176 |
| Sonnet 5.5 | $0.00003 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
vulyk-resume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Resume: "$ARGUMENTS" (the spec slug).
bash scripts/cycle.sh resume docs/specs/<slug>. Print exactly what it prints: thecycle: <slug> - resumedline and its JSON, which carriesstaleandheldfields.heldnon-empty means a driver claim is still on disk; resume never removes it. Look at your task list (/tasks, the Workflow run): a run still going is finishing its agent in flight, so wait for its notification before step 3. Only a run that is gone (session restarted, run ended without releasing) is dead: then run thereleasecommand resume printed. A second driver over a live one's worker overwrites its files. A run that had not reached its next step when you resumed never saw the pause: it simply goes on building, so skip step 3 and wait for its notification.- If
stale: true, the tree moved (a manual commit) while the loop was paused: the open round, if any, is stale, and the next roundadvanceopens re-reviews the new diff. The tier's ceiling still counts it. - Relaunch with
/vulyk-build <slug>, always a fresh run: the solo path at Tier 1-2, the hive path at Tier 3-4. On the hive path, once the stamp is resolved, runbash scripts/telemetry.sh record driver_relaunched 1 0 --spec <slug> --ref relaunch:<slug>:$stampbefore the launch. Never passresumeFromRunIdor any equivalent: a cached status replayed after the owner touched the tree is exactly the wrong answer.advancere-derives everything from disk, so a story already done or a seat already recorded is never dispatched again.
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.
- 13d ago Changed · +6 lines e6929ebd8740
- 1mo ago Changed · -5 lines 65ece3800a08
- 1mo ago Changed · +3 lines 7780a0665c80
- 1mo ago First seen · 21 lines · 17 tokens per session scan A 0364728c91c2
vulyk-resume is a command published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 440 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other commands, from other repositories
flow
End-to-end feature/bug/refactor pipeline (plan → start → implement → QA → ship → address → cleanup) with an interactive gate at every phase. Resumable via /orc:resume. --jira links a ticket. Workspace-aware.
jira-breakdown
Turn a feature brief, PRD, or existing Epic into a full Jira hierarchy behind a preview gate.
jira
Manage Jira tickets via acli, and bind/unbind a ticket key to the current orc session — persists jiraTicket in .orc/orc.json + checkpoint.md so /orc:status, /orc:resume, and /orc:ship all see the link.
setup
Run-once repo interview that writes the tracker layer (docs/agents/issue-tracker.md, triage-labels.md, domain.md) with recommended answers.
postmortem
Author a blameless incident postmortem — timeline, root causes, action items — filing each P0 action item as a tracker issue. Status reaches Final only when all P0 items close.
triage
Intake for any report (issue, PR, Jira, Sentry, paste): check it is valid, then brief, file, park or reject it.