handoff-context

handoff-context is a command for Claude Code from clafollett/lafollettlabs-claude-plugins. It costs 0 tokens per session (749 once invoked), scanned A, original, MIT.

A command that saves the current coding session's working state in a structured JSON file so it can be resumed after clearing the session.

In plain words
What is it for?
Use it to archive previous handoffs, update ignored context files, record completed and pending work, and resume later with /resume-context.
Why use it?
It prevents important progress, next steps, and blockers from being lost between sessions while avoiding duplicate follow-up work.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the context-handoff plugin — 2 commands, 1 hook shipped together

Good fit Use it to archive previous handoffs, update ignored context files, record completed and pending work, and resume later with /resume-context.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/clafollett/lafollettlabs-claude-plugins/handoff-context
Install

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.

Clone the repo
git clone --depth 1 https://github.com/clafollett/lafollettlabs-claude-plugins

Made for: Claude Code.

Or install context-handoff, the plugin that ships this one along with the rest of its 2 commands, 1 hook.

Wrote 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.

agentmods badge for handoff-context

README.md
[![agentmods](https://agentmods.dev/badge/commands/clafollett/lafollettlabs-claude-plugins/handoff-context/github.svg)](https://agentmods.dev/commands/clafollett/lafollettlabs-claude-plugins/handoff-context)
Your own site
<a href="https://agentmods.dev/commands/clafollett/lafollettlabs-claude-plugins/handoff-context"><img src="https://agentmods.dev/badge/commands/clafollett/lafollettlabs-claude-plugins/handoff-context/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.

agentmods 80×15 button for handoff-context

Your own site · 80×15
<a href="https://agentmods.dev/commands/clafollett/lafollettlabs-claude-plugins/handoff-context"><img src="https://agentmods.dev/badge/commands/clafollett/lafollettlabs-claude-plugins/handoff-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 749 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00749
Opus 5 $0.00000 $0.00375
Sonnet 5 $0.00000 $0.00150
Haiku 4.5 $0.00000 $0.00075

Measured 10d ago against content hash 9041aa5d8e59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

handoff-context 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 10d 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.

plugins/context-handoff/commands/handoff-context.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Context

Save the current session's working state to a structured JSON file so it survives a /clear and can be resumed later via /resume-context.

Steps

  1. Ensure .context/ exists at the project root. Create it if missing.

  2. Check .gitignore — if .context/ is not already ignored, append it with a comment:

    # Context handoff files (session state, not committed)
    .context/
    
  3. Archive any existing handoff — if .context/context-handoff.json exists, rename it to .context/context-handoff.<YYYYMMDD>T<HHMMSS>.json using the current UTC timestamp before writing the new one.

  4. Self-dedupe against current session — before building the handoff JSON, review the completed items you're about to write. Any item that appears in both completed and next_steps should be removed from next_steps. This prevents the next session from picking up work that was already finished in this session.

    Also check if any blocked items were resolved during this session (i.e., they appear in completed or are no longer blocked based on conversation context). Remove resolved blockers from the blocked array.

  5. Diff against prior handoff — if an archived handoff exists (.context/context-handoff.<timestamp>.json), read the most recent one and check for items in your new next_steps that already appear in the prior handoff's completed. Remove them — they're stale leftovers from a previous session that were never cleaned up.

  6. Analyze the full conversation and build a JSON object with this schema:

{
  "version": "1.0",
  "created_at": "<ISO-8601 UTC>",
  "project_root": "<absolute path>",
  "branch": "<current git branch>",
  "task": {
    "goal": "<what we were trying to accomplish>",
    "why": "<motivation / context behind the task>"
  },
  "state": {
    "completed": ["<items finished>"],
    "in_progress": ["<items started but not done>"],
    "blocked": ["<items blocked, with reasons>"]
  },
  "decisions": [
    {
      "decision": "<what was decided>",
      "rationale": "<why>",
      "alternatives_rejected": ["<options considered but not chosen>"]
    }
  ],
  "constraints": ["<discovered constraints, edge cases, gotchas>"],
  "issues": ["<bugs, warnings, problems encountered>"],
  "files_modified": ["<files changed in this session>"],
  "next_steps": ["<ordered list of what to do next>"],
  "notes": "<any other important context that doesn't fit above>"
}

Read the full file on GitHub · 70 lines

Changes

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.

  1. 10d ago First seen · 70 lines · 0 tokens per session scan A 9041aa5d8e59

Subscribe to this mod's changes

handoff-context is a command published in the GitHub repository clafollett/lafollettlabs-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 749 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.