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.
git clone --depth 1 https://github.com/andrei-isvoran96/claude-skill-labWrote 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/andrei-isvoran96/claude-skill-lab/handoff)<a href="https://agentmods.dev/commands/andrei-isvoran96/claude-skill-lab/handoff"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/handoff/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/andrei-isvoran96/claude-skill-lab/handoff"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/handoff.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 | $0.00000 | $0.01369 |
| Opus 5 | $0.00000 | $0.00685 |
| Sonnet 5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a structured handoff brief from the current session to a file, then print the exact one-liner the user can paste into a fresh claude session to continue the work without re-loading the whole conversation. Use this when the context window is filling up but the work isn't done.
Arguments
This command accepts an optional short slug as $ARGUMENTS to name the handoff. Examples:
/handoff— uses a timestamp slug/handoff auth-refactor— usesauth-refactoras the slug (so multiple in-flight handoffs can coexist)
The slug is sanitized (lowercase, non-alphanumeric → -, truncated to 40 chars).
Steps
-
Build the slug and target path.
- If
$ARGUMENTSis empty, slug = current UTC timestamp inYYYYMMDD-HHMMform. - Otherwise, sanitize
$ARGUMENTS: lowercase, replace any run of non-alphanumeric chars with-, trim leading/trailing-, truncate to 40 chars. - Target file:
<HANDOFF_DIR>/<slug>.md(default.claude/handoffs/<slug>.md). - Also maintain a stable pointer at
<HANDOFF_DIR>/latest.md(overwrite each run) so the resume one-liner is the same every time. mkdir -p <HANDOFF_DIR>if needed.
- If
-
Capture the operational state of the working tree. Run these in parallel:
git status --short git diff --stat git log --oneline -5 git branch --show-currentYou'll reference these in the brief so the fresh session knows what's modified, what's committed, and where it sits.
-
Draft the brief. It must be short enough to be cheap to load into a fresh context, complete enough that the new session doesn't need to ask "what was I doing?". Use this exact skeleton — fill every section, write
(none)if a section genuinely doesn't apply:# Handoff — <slug> *Written <UTC timestamp> from session on branch `<branch>`.* ## Goal <1–2 sentences: what is the user ultimately trying to accomplish in this thread of work? Not "what we did in this session" — the underlying objective.> ## Current state - <bullet per concrete change made or decision taken so far> - <include file paths the user has touched, e.g. `src/auth/middleware.ts:42`> ## Working tree<paste the
git status --shortoutput verbatim>Branch: `<current branch>`. Recent commits:<paste the
git log --oneline -5output>## Where we left off <1–3 sentences: the immediate next step. Be specific — "add the failing-case test for X in path/to/test.ts" beats "continue with tests".> ## Key context the fresh session needs - <non-obvious facts discovered this session: hidden constraints, API quirks, broken assumptions corrected> - <decisions already made and *why* — so the new session doesn't relitigate them> ## Already tried, don't repeat - <approaches that looked promising but failed, with one-line reason — so the new session doesn't burn context rediscovering> ## Open questions for the user - <things the user needs to weigh in on before fresh Claude can proceed; if none, write `(none)`>
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.
- 9d ago First seen · 107 lines · 0 tokens per session scan A 0fe0a101de72
handoff is a command published in the GitHub repository andrei-isvoran96/claude-skill-lab (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,369 tokens. 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
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.