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.
git clone --depth 1 https://github.com/clafollett/lafollettlabs-claude-pluginsWrote 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/clafollett/lafollettlabs-claude-plugins/handoff-context)<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.
<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>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 | $0.00000 | $0.00749 |
| Opus 5 | $0.00000 | $0.00375 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
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.
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
-
Ensure
.context/exists at the project root. Create it if missing. -
Check
.gitignore— if.context/is not already ignored, append it with a comment:# Context handoff files (session state, not committed) .context/ -
Archive any existing handoff — if
.context/context-handoff.jsonexists, rename it to.context/context-handoff.<YYYYMMDD>T<HHMMSS>.jsonusing the current UTC timestamp before writing the new one. -
Self-dedupe against current session — before building the handoff JSON, review the
completeditems you're about to write. Any item that appears in bothcompletedandnext_stepsshould be removed fromnext_steps. This prevents the next session from picking up work that was already finished in this session.Also check if any
blockeditems were resolved during this session (i.e., they appear incompletedor are no longer blocked based on conversation context). Remove resolved blockers from theblockedarray. -
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 newnext_stepsthat already appear in the prior handoff'scompleted. Remove them — they're stale leftovers from a previous session that were never cleaned up. -
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>"
}
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.
- 10d ago First seen · 70 lines · 0 tokens per session scan A 9041aa5d8e59
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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.