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-handoff.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-handoff)<a href="https://agentmods.dev/commands/black-coffe/vulyk/vulyk-handoff"><img src="https://agentmods.dev/badge/commands/black-coffe/vulyk/vulyk-handoff.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 5.1 | $0.00016 | $0.00486 |
| Opus 5 | $0.00008 | $0.00243 |
| Sonnet 5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
vulyk-handoff 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.
What it actually says
The build-state view, regenerated first so the handoff sits beside a current one rather than whatever was last written:
!bash scripts/state.sh
The mechanical handoff skeleton has already been written to disk:
!bash .claude/hooks/handoff.sh dump
The first line of the output above is the absolute path to the handoff .md file; the second line is the context size at dump time. If the output is empty, the dump failed (usually: no Python 3 on PATH) — tell the user instead of guessing.
Your job is to turn that skeleton into a document the next session can resume from without re-asking anything:
- Read the file at that path.
- Rewrite the
## Summarysection from what actually happened in THIS session. Invent nothing — if something did not happen, do not write it. Structure:- What we are doing and why — the task in 2–4 sentences, including the goal, not just the actions.
- Where we stopped — the current factual state: what is done and verified, what is written but not yet tested.
- Next step — the concrete first action for the new session, not a general direction.
- Decisions made — the chosen options and why (the most valuable part: this reasoning cannot be reconstructed later).
- Dead ends — what was already tried and did not work, including false diagnoses and wrong assumptions that had to be discarded, so the next session does not step on the same rake.
- What you will need — key files, commands, paths, environment variables, external resources.
- In the YAML frontmatter, flip
enriched: falsetoenriched: true. - Touch nothing except the
## Summarysection and theenrichedfield — everything else was assembled mechanically and must stay as-is.
Finish with one short line to the user: the file path plus a reminder that /clear (or exit + restart) is now safe — the next session in this project picks the handoff up automatically.
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 · 31 lines · 16 tokens per session scan A 6d7b5c334598
vulyk-handoff is a command published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 486 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
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
evolve
A knowledge-review workflow that groups repeated lessons and turns them into reusable commands, automatic skills, or separate agents. A command is user-triggered, a skill is an automatic behaviour, and an agent handles a complex multi-step task.
memory
A project-memory manager that keeps current progress, technical decisions, problems, and reusable patterns in Markdown files inside a memory-bank folder.
status
A project-status command that checks a code repository and its supporting project notes. The supplied description is in Chinese and lists checks for Git, a memory bank, dependencies, environment settings, components, and conflicts.
context
A project-context manager for coding-agent sessions. It loads the project’s goals, technology choices, constraints, current phase, related documents, and task details from files such as progress.md.
catchup
A command for quickly rebuilding project context after the conversation has been cleared. It reads key project documents, recent Git changes, and available session history, then summarizes the current state.