handoffs

handoffs is a skill for Claude Code from flurdy/agent-skills. It costs 55 tokens per session (7,607 once invoked), scanned B, original, MIT.

A tool for finding saved handoff notes from earlier coding sessions. A handoff records enough context to continue unfinished work later.

In plain words
What is it for?
Use it to list handoffs, inspect the current repository's saved sessions, and choose a thread to resume.
Why use it?
It helps recover previous work when a session ended, a branch was removed, or several possible handoffs exist.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

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/flurdy/agent-skills/handoffs
Any agent
npx skills add flurdy/agent-skills --skill handoffs
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code.

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 handoffs

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/handoffs.svg)](https://agentmods.dev/skills/flurdy/agent-skills/handoffs)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/handoffs"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/handoffs.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,607 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00055 $0.07607
Opus 5 $0.00028 $0.03803
Sonnet 5 $0.00011 $0.01521
Haiku 4.5 $0.00006 $0.00761

Measured 5d ago against content hash e04c46b97706, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

handoffs scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/archive.sh, scripts/list.sh, tests/test_list.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

_⚠️ {unresolved} handoff(s) could not be matched to any repo or directory (recorded path is invalid or gone). Run `grep -L "Repo root:" ~/.claude/handoffs/*.md` to find them._
skills/handoffs/SKILL.md · 455 lines

How it starts

The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoffs — Pick a saved session to resume

Browse handoff files written by /wrap-up (in ~/.claude/handoffs/) and pick one to resume. Companion to /wrap-up (the writer) and /landscape (the morning orienter).

When to use

  • Starting a session and wanting to pick up a thread from a previous one.
  • After /landscape flagged that recent handoffs exist for this repo.
  • Searching for an older thread — ls ~/.claude/handoffs/ is grep-friendly, but this skill renders the metadata table.

Not sure whether to resume a handoff or start fresh work? That's a morning orientation call, not a handoffs call — run /landscape first. Its **Next:** line arbitrates resume-a-handoff vs /next safe from the full picture (Jira, PRs, beads, working copy). Come here once you've decided to resume a thread.

What it does

  1. List handoffs across all repos, with per-repo counts.
  2. Fully detail handoffs in the current repo as a pickable table, flagging which are superseded by a newer handoff, done (PR merged, all beads closed, or Jira ticket Done), or stale (branch gone / PR closed).
  3. Summarise handoffs in other repos (count per repo, not full listing).
  4. Optionally archive confirmed superseded, done, stale, or assisted-review handoffs to keep the picker focused, including safe workspace-member rows through separate per-repo confirmation.
  5. Prompt you to pick one — only handoffs for the current repo and workspace members are pickable.
  6. On pick, render the resume block inline and surface the cd if the recorded worktree differs from pwd.

Important — what this skill cannot do

  • It cannot resume for you. It surfaces the resume block; you read it and act on the next step.
  • It cannot rename the session for you. On load it prints the active client's paste-ready command (§5): /name {slug} in Pi and /rename {slug} in Claude Code. Only you typing it triggers a rename.
  • It cannot pick handoffs from unrelated repos. That is a deliberate guard — running commands against the wrong repo is the failure mode it prevents. To resume a handoff in an unrelated repo, cd there and run /handoffs again. Exception: repos in the same multi-repo workspace are listed and pickable (§2b/§4b), because from a workspace root they'd otherwise be invisible; picking one requires an explicit cd before any repo-scoped command runs.
  • It never deletes handoff files. The opt-in archive steps (§3b–§3e) only move explicitly confirmed candidates into ~/.claude/handoffs/archive/ — they stay on disk and greppable.

Read the full file on GitHub · 455 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 455 lines · 55 tokens per session scan B e04c46b97706

Subscribe to this mod's changes

handoffs is a skill published in the GitHub repository flurdy/agent-skills (8 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 7,607 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens