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 skills/shawnla90/recursive-drift/context-handoffnpx 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.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 | $0.00045 | $0.00462 |
| Opus 5 | $0.00023 | $0.00231 |
| Sonnet 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 5d 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.
- 5d 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 5mo ago), licensed MIT. It adds 45 tokens to every session and 462 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
project-butler
Project memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organization, document archiving, language switching, versioned update logs, rule review, status, wiki sync, and context recovery. Use for /project-butler, setup/初始化, foundation setup, profile setup, end session/收工…
vc-context-discovery
Discover and load all relevant context for the current task. Lists feature group nested files with full paths, loads process/context/ files by domain routing. Called at the start of every agent session.
vc-generate-context
Generate or update the project's authoritative repository context at process/context/all-context.md. Use when repo context is missing, stale, or contradicted by code.
doncheli-context-health
Report the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".
context-optimizer
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
compact-guard
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.