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 skills add shawnla90/recursive-drift --skill context-handoffgit clone --depth 1 https://github.com/shawnla90/recursive-driftWrote 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/skills/shawnla90/recursive-drift/context-handoff)<a href="https://agentmods.dev/skills/shawnla90/recursive-drift/context-handoff"><img src="https://agentmods.dev/badge/skills/shawnla90/recursive-drift/context-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/skills/shawnla90/recursive-drift/context-handoff"><img src="https://agentmods.dev/badge/skills/shawnla90/recursive-drift/context-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 | $0.00045 | $0.00462 |
| Opus 5.5 | $0.00018 | $0.00185 |
| Sonnet 5.5 | $0.00009 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
context-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 2mo 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
Context Handoff
Generate a structured handoff document that preserves session context for the next Claude Code agent.
When to Invoke
- End of any session that made meaningful changes
- Before switching between machines
- When context window is getting large and a fresh session is needed
- User says
/handoff, "wrap up", "hand off", or "create a handoff"
Output Location
Write to: .claude/context-handoff.md
This file is checked by every new session via the MEMORY.md auto-load instruction.
Handoff Template
Write the handoff using this exact structure:
# Context Handoff
> Generated: YYYY-MM-DD HH:MM | Machine: [identifier] | Session: [brief label]
## What Was Done This Session
[Bullet list of completed work. File paths, not summaries.]
## Current State
- **Git**: [branch, clean/dirty, last commit hash + message]
- **Uncommitted changes**: [list or "none"]
- **Blocked on**: [anything that couldn't be completed and why]
## Next Steps
[Ordered list of what the next session should pick up. Include file paths and specific instructions.]
## Key Decisions Made
[Any architectural or approach decisions the next agent needs to know about to avoid re-litigating.]
## Files to Read First
[Top 3-5 files the next session should read to get oriented, in priority order.]
Rules
- Be specific -- file paths, commit hashes, line numbers. Vague handoffs are useless.
- Don't summarize the whole repo -- only include what changed THIS session.
- Include blockers -- if something failed or was skipped, say why.
- Keep it under 100 lines -- this is a handoff, not a novel.
- Always run
git statusandgit log -1 --onelinebefore writing the handoff to capture accurate state.
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.
- 2mo ago First seen · 56 lines · 45 tokens per session scan A a6f1e776a94c
context-handoff is a skill published in the GitHub repository shawnla90/recursive-drift (18 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 462 once invoked, about $0.0002 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 2026-08-30.
context-handoff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| context-handoffshawnla90/recursive-drift | Skill | 18 | 7mo ago | MIT | A | 45 | Claude Code, Codex |
| project-butlerJamesShi96/project-butler | Skill | 374 | 3mo ago | MIT | A | 133 | Claude Code, Codex |
| kanso-handoffblakecyze/kanso | Skill | 5 | 2d ago | MIT | A | 86 | Claude Code |
| minimax-m3-long-contextmadebyaris/advance-minimax-m3-cursor-rules | Skill | 126 | 4mo ago | MIT | A | 101 | Cursor |
| resume-sessionmultiplex-ai/muggle-ai-teams | Skill | 2 | 12d ago | MIT | A | 29 | Claude Code, Codex |
| asidemultiplex-ai/muggle-ai-teams | Skill | 2 | 12d ago | MIT | A | 24 | Claude Code, Codex |
| evolvemultiplex-ai/muggle-ai-teams | Skill | 2 | 12d ago | MIT | A | 11 | Claude Code, Codex |