handoff

handoff is a skill for Claude Code, Codex from lwalden/AIAgentMinder. It costs 8 tokens per session (586 once invoked), scanned A, original, MIT.

A session checkpoint that records the current state of coding work so it can be resumed later. It also records important design decisions and a few priority notes for future sessions.

In plain words
What is it for?
Use it before stopping work to record changed files, progress, active sprint status, decisions, known technical debt, and the next priority items.
Why use it?
It prevents progress, decisions, and unfinished work from being lost when a session ends.

Skill for Claude CodeCodex

Part of the aiagentminder plugin — 15 skills, 16 agents, 5 hooks shipped together

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.

agentmods
npx agentmods add skills/lwalden/aiagentminder/handoff
Any agent
npx skills add lwalden/AIAgentMinder --skill handoff
Clone the repo
git clone --depth 1 https://github.com/lwalden/AIAgentMinder

Made for: Claude Code, Codex.

Or install aiagentminder, the plugin that ships this one along with the rest of its 15 skills, 16 agents, 5 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/lwalden/aiagentminder/handoff.svg)](https://agentmods.dev/skills/lwalden/aiagentminder/handoff)
Your own site
<a href="https://agentmods.dev/skills/lwalden/aiagentminder/handoff"><img src="https://agentmods.dev/badge/skills/lwalden/aiagentminder/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.00586
Opus 5 $0.00004 $0.00293
Sonnet 5 $0.00002 $0.00117
Haiku 4.5 $0.00001 $0.00059

Measured 5d ago against content hash 87d74405ea21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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.

skills/handoff/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aiagentminder:handoff - Session Checkpoint

Capture current state so work can be resumed cleanly. Run this before ending a session.


Steps

1. Assess Current State

Review what happened this session:

  • What files were created or modified?
  • What was the goal and how far did we get?
  • Any decisions made that should be in DECISIONS.md?
  • Is there an active sprint? Check if SPRINT.md contains **Status:** in-progress. If so, note which issue was active and the done/in-progress/todo/blocked counts.

2. Update DECISIONS.md (if applicable)

If any of these happened this session, add an ADR entry:

  • Chose a library, framework, or tool
  • Designed an API or data contract
  • Selected an auth approach
  • Changed a data model
  • Made a build/deploy decision
  • Implemented a known workaround (also add a row to the ## Known Debt section)

Use the format already established in DECISIONS.md. Always include alternatives considered and the tradeoff accepted — a decision without alternatives is an assertion, not a record.

3. Write 2-3 Priority Items to Auto-Memory

Locate the project's auto-memory file at: ~/.claude/projects/[project-path-hash]/memory/MEMORY.md

Append or update a "Next Session" section:

## Next Session
- [Most important thing to know picking up next — be specific, not vague]
- [Second priority or open question]
- [Third item only if genuinely needed]

Keep each bullet to one sentence. Do not exceed 3 items. Specificity matters: "Continue API work" is not useful; "Implement POST /users/:id — GET is done, need POST with request validation" is.

4. Commit

git add DECISIONS.md
git commit -m "handoff: session checkpoint [today's date]"

Only stage files that were modified. Do NOT modify SPRINT.md during handoff — sprint state is updated during sprint execution.

5. Print the Briefing

Session handoff complete.

This session:
- [what was accomplished — specific files/features/fixes]

State of things:
- [what's working, what's not, what's in progress]
[if sprint active:]
Sprint [n]: [done]/[total] issues done[, [blocked] blocked]
Currently on: S[n]-[seq] — [issue title]

Next session should:
1. [specific first action]
2. [specific second action]

Blockers for human:
- [anything requiring human action, or "None"]

Read the full file on GitHub · 83 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. 5d ago First seen · 83 lines · 8 tokens per session scan A 87d74405ea21

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 586 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories

inspector-workbench

Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…

CopilotKit/CopilotKit · 112 tokens

obsidian-bases

Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.

AgriciDaniel/claude-obsidian · 69 tokens

save

Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…

AgriciDaniel/claude-obsidian · 80 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

wiki-mode

Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…

AgriciDaniel/claude-obsidian · 83 tokens