resume-context

resume-context is a command for Claude Code from clafollett/lafollettlabs-claude-plugins. It costs 0 tokens per session (567 once invoked), scanned A, original, MIT.

A command for restoring a saved project handoff. A context handoff is a file that records the previous session's task, state, completed work, and next steps.

In plain words
What is it for?
Resuming work from .context/context-handoff.json. If no active handoff exists, it lists available archived handoffs.
Why use it?
It helps a new session understand where earlier work stopped. It also identifies next steps that were already completed in an archived handoff.

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 Resuming work from .context/context-handoff.json. If no active handoff exists, it lists available archived handoffs.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/clafollett/lafollettlabs-claude-plugins/resume-context"><img src="https://agentmods.dev/badge/commands/clafollett/lafollettlabs-claude-plugins/resume-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 567 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 $0.00567
Opus 5 $0.00000 $0.00283
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00057

Measured 11d ago against content hash 40883914460e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

resume-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 11d 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/resume-context.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume Context

Load a previously saved context handoff and orient this session around it.

Steps

  1. Read .context/context-handoff.json from the project root.

    • If the file does not exist, check for any .context/context-handoff.*.json files and list them. Tell the user no active handoff was found and show available history.
  2. Parse the JSON and verify it has the expected schema (version, task, state, etc.).

  3. Diff against prior handoff — find the most recent .context/context-handoff.<timestamp>.json archive file (sort by filename timestamp, pick the latest). If one exists:

    • Parse it and extract its state.completed array.
    • Compare the current handoff's next_steps against the prior completed items. Use substring/keyword matching — items won't be verbatim identical but will reference the same PR numbers, issue numbers, or key phrases.
    • Flag any next_steps that appear already completed in the prior session — these are stale and should be called out in the briefing as "already done (prior session)".
    • Also check current blocked items against prior completed — a blocker that was resolved in the prior session should be flagged as "potentially unblocked".
    • If no archived handoff exists, skip this step silently.
  4. Orient the session — print a concise briefing for the user:

    • What we were working on (task goal + why)
    • Current state (what's done, what's in progress, what's blocked)
    • Key decisions made and constraints discovered
    • Immediate next steps (with any stale items from step 3 clearly marked)
    • Current branch and any uncommitted changes (check live git status, don't just trust the file)
  5. Archive the handoff — rename the file to .context/context-handoff.<YYYYMMDD>T<HHMMSS>.json using the current UTC timestamp. This prevents stale context from being loaded in a future session.

  6. Verify against reality — the handoff was written in a prior session and may be stale:

    • Confirm the branch still exists and is checked out
    • Spot-check that key files mentioned in files_modified exist
    • If anything doesn't match, flag it to the user before proceeding

Read the full file on GitHub · 38 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. 11d ago First seen · 38 lines · 0 tokens per session scan A 40883914460e

Subscribe to this mod's changes

resume-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 567 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.