Borrowing it
Nothing to install: this file belongs to Aptica-Solutions/a-mcp-runmeter. 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/Aptica-Solutions/a-mcp-runmeter/main/.claude/commands/handoff.mdgit clone --depth 1 https://github.com/Aptica-Solutions/a-mcp-runmeterWrote 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/aptica-solutions/a-mcp-runmeter/handoff)<a href="https://agentmods.dev/commands/aptica-solutions/a-mcp-runmeter/handoff"><img src="https://agentmods.dev/badge/commands/aptica-solutions/a-mcp-runmeter/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/aptica-solutions/a-mcp-runmeter/handoff"><img src="https://agentmods.dev/badge/commands/aptica-solutions/a-mcp-runmeter/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 | $0.00486 |
| Opus 5 | $0.00000 | $0.00243 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
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 7d 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
Write a session handoff note and prepare for context reset. Follow these steps in order.
Step 1 — Read Current State
Read these files before writing anything:
AI-TASKS.md— note which tasks changed status this session (look for [~] and recent [x])CONTEXT.md— acknowledge any prior handoff that was in effect
Step 2 — Draft Handoff Note
Compose a structured handoff using this exact format:
# Session Handoff — [YYYY-MM-DD]
## Accomplished This Session
- [bullet per completed or meaningfully advanced item]
## In Progress — Pick Up Here
[~] [task name or description]
State: [describe exactly where this is — e.g., "file X is done, file Y still needs the Y section"]
Next action: [single sentence — the first thing to do to resume this task]
## Decisions Made
- [decision]: [reason — one line each, only decisions that would surprise a fresh session]
## Open Blockers
- [anything unresolved, waiting on user input, or deferred]
(write "None" if clear)
## Next Step
> [One sentence. The exact first action for the next session.]
## Files Touched (non-obvious only)
- [path] — [why it matters]
Keep it compact — the goal is a cold-start brief, not a full log. Omit sections that are empty except Blockers (write "None" there explicitly).
Step 3 — Write to CONTEXT.md
Write the completed handoff note to CONTEXT.md, replacing any prior content.
Step 4 — Confirm and Hand Off
Show the written handoff to the user. Then output exactly:
Handoff written to CONTEXT.md.
Run /clear to reset the session. The next session will read this note automatically.
If the user asks to revise the handoff, update CONTEXT.md and confirm again.
Notes
- Do not commit
CONTEXT.md— it is session state, not source - If AI-TASKS.md has changed tasks, ensure it is saved before writing the handoff
- The handoff replaces the session checkpoint signal — use /handoff instead of printing the checkpoint block when resetting mid-PBI
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.
- 7d ago First seen · 70 lines · 0 tokens per session scan A d7f3b396f52f
handoff is a command published in the GitHub repository Aptica-Solutions/a-mcp-runmeter (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 486 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 2026-09-01.
Other commands, from other repositories
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
revise-claude-md
Update CLAUDE.md with learnings from this session.
check-structure
Check context/project/ against the shape rules and propose the smallest tree that passes them. Propose first, apply only on "apply".
add-to-context
Promote reviewed journal facts into context/project/ (propose, then apply).