What is resuming-from-handoff?

A session-resume guide for finding and reviewing handoff files from earlier coding work.

It helps locate the right handoff, summarize the saved project state, and confirm what to resume.

It prevents you from guessing which previous session to continue or losing context between sessions.

resuming-from-handoff — Skill for Claude Code by se4thvin

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/se4thvin/context-handoff

agentmods

npx agentmods add skills/se4thvin/context-handoff/resuming-from-handoff

Made for: Claude Code.

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/se4thvin/context-handoff/resuming-from-handoff/github.svg)](https://agentmods.dev/skills/se4thvin/context-handoff/resuming-from-handoff)

Your own site

<a href="https://agentmods.dev/skills/se4thvin/context-handoff/resuming-from-handoff"><img src="https://agentmods.dev/badge/skills/se4thvin/context-handoff/resuming-from-handoff/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/se4thvin/context-handoff/resuming-from-handoff"><img src="https://agentmods.dev/badge/skills/se4thvin/context-handoff/resuming-from-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 819 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00819
Opus 5	$0.00030	$0.00409
Sonnet 5	$0.00012	$0.00164
Haiku 4.5	$0.00006	$0.00082

Measured 10d ago against content hash 207759794285, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

resuming-from-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 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.

skills/resuming-from-handoff/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resuming From a Handoff

Overview

Find the most relevant handoff file for the current project, summarize it, and confirm with the user before continuing work. Never silently assume which handoff to load when more than one exists.

When to use

Fire this skill when ANY of:

The user invokes /handoff-resume (with or without a numeric argument).
The user says: "pick up where we left off", "continue from last session", "what was I working on", "resume from yesterday".
The user starts a session by referencing prior work that's likely captured in a handoff.

What to do

Resolve search directories in this order:
- ./.handoffs/ (project-local) — always check.
- $HANDOFF_DIR — if set AND different from ./.handoffs/, also check.
List handoffs by modification time, newest first. If both dirs apply, merge the lists by mtime.
```
ls -1t ./.handoffs/*.md 2>/dev/null
```
Optionally include $HANDOFF_DIR/*.md too.
Branch on count:
- Zero handoffs: Tell the user "No handoffs found in <path>. Use /handoff next session to create one." Stop.
- Exactly one handoff: Read it. Show a 3-5 line summary covering: project, timestamp, current task, next steps. Ask: "Continue from these next steps?" Wait for confirmation before acting.
- Multiple handoffs: If the user passed a number (/handoff-resume 2), skip to that index (1-based, newest-first). Otherwise show a numbered picker:
```
Found 3 handoffs:
1. 2026-05-12 14:30 — "Refactoring auth middleware — two helpers extracted..."
2. 2026-05-12 09:15 [before-refactor] — "About to split the auth middleware..."
3. 2026-05-11 17:42 — "WIP: parser bug in token stream."

Which one? (1-3, or "q" to cancel)
```
  Preview text: the first non-empty line under ## Current task in each file, truncated to ~70 chars. Wait for the user's choice. Then load it, summarize, and confirm before acting.
After loading, summarize the handoff in 3-5 lines. Do NOT dump the full file contents back to the user — they wrote it. Show:
- Project + timestamp + label (if any)
- Current task (one line)
- Top 1-3 next steps
- Any blockers

Read the full file on GitHub · 65 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.

10d ago First seen · 65 lines · 59 tokens per session scan A 207759794285

Subscribe to this mod's changes

resuming-from-handoff is a skill published in the GitHub repository se4thvin/context-handoff (2 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 819 once invoked, about $0.0003 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.

Claude Code Productivity claude claude-code-plugin cli context-management handoff

alive:system-cleanup

The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.

alivecontext/alive · 52 tokens

alive:world

The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.

alivecontext/alive · 63 tokens

alive:bundle

Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.

alivecontext/alive · 34 tokens

alive:settings

The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…

alivecontext/alive · 84 tokens

alive-cleanup

System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.

alivecontext/alive · 20 tokens

alive-daily

Morning operating system -- sync inputs, read everything, surface priorities, show the day.