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.
npx agentmods add commands/thatsuperdev/llm-handoff/resumegit clone --depth 1 https://github.com/thatsuperdev/llm-handoffWrote 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/thatsuperdev/llm-handoff/resume)<a href="https://agentmods.dev/commands/thatsuperdev/llm-handoff/resume"><img src="https://agentmods.dev/badge/commands/thatsuperdev/llm-handoff/resume.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 | $0.00011 | $0.00496 |
| Opus 5 | $0.00005 | $0.00248 |
| Sonnet 5 | $0.00002 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00050 |
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 3d 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
You are starting a new session. A handover.md was left by the previous session to brief you. Load it and prepare to continue.
Steps
1. Read the handover
Read handover.md from the project root (or git rev-parse --show-toplevel).
If it does not exist, tell the user:
No handover.md found in this directory. Either no handover was created, or you may
need to check a different directory. Run /llm-handoff:create in the previous session
before switching to this one.
2. Verify repository state
Run:
git status --short
git log --oneline -5
Compare the output to the Repository state section in handover.md.
If anything conflicts (different branch, unexpected uncommitted files, commits that don't match), report it:
Warning: Current state differs from handover.md.
- Expected branch: <from handover> Got: <actual>
- Expected last commit: <from handover> Got: <actual>
Investigate before proceeding — the handover may be stale or from a different worktree.
3. Brief the user
Report in this exact structure:
Handover loaded.
Previous LLM: <model and tool from handover>
Generated: <timestamp>
Goal: <session goal>
Completed:
- <item>
- <item>
In progress:
<what was being worked on>
Ready to continue with:
→ Step 1: <first next step title>
File: <path>
Action: <what to do>
Verify: <how to confirm>
Continue? (I'll wait for your go-ahead before making any changes.)
4. Wait for confirmation
Do not make any changes until the user confirms. If the user says "yes" or "go", begin with Next steps item 1 exactly as described in the handover.
5. After completing each step
Check it off in your working context (you do not need to edit handover.md). When all next steps are complete, ask the user if they want to update or remove handover.md.
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.
- 3d ago First seen · 75 lines · 11 tokens per session scan A b07c95ab7d0f
resume is a command published in the GitHub repository thatsuperdev/llm-handoff (1 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 496 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
assets
Inventory .claude-design/ / — file counts, types, locations.
phoenix
Toggle Phoenix mode on/off — recurring context recycling for zero-click continuity.
budget
View context budget allocation — code vs conversation vs memory breakdown.
obliviate
Analyze and archive stale memories — semantic context pruning.
remembrall-uninstall
Clean up all remembrall data and remove the bridge from settings.json.
statistics
View ambient learning statistics — file hotspots, patterns, recurring errors.