session-handoff

session-handoff is a skill for Claude Code from kraulerson/solo-orchestrator. It costs 51 tokens per session (1,033 once invoked), scanned A, original, MIT.

A handoff document for recording the current work so another developer or agent can continue after an interruption or at the end of a session.

In plain words
What is it for?
Use it before a context limit, computer restart, operator change, or end-of-day pause when a task is unfinished.
Why use it?
It avoids losing important context when work moves to someone else, a new session, or a later time.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it before a context limit, computer restart, operator change, or end-of-day pause when a task is unfinished.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kraulerson/solo-orchestrator/session-handoff
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.

Any agent
npx skills add kraulerson/solo-orchestrator --skill session-handoff
Clone the repo
git clone --depth 1 https://github.com/kraulerson/solo-orchestrator

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 session-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/kraulerson/solo-orchestrator/session-handoff/github.svg)](https://agentmods.dev/skills/kraulerson/solo-orchestrator/session-handoff)
Your own site
<a href="https://agentmods.dev/skills/kraulerson/solo-orchestrator/session-handoff"><img src="https://agentmods.dev/badge/skills/kraulerson/solo-orchestrator/session-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.

agentmods 80×15 button for session-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/kraulerson/solo-orchestrator/session-handoff"><img src="https://agentmods.dev/badge/skills/kraulerson/solo-orchestrator/session-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,033 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00051 $0.01033
Opus 5 $0.00026 $0.00517
Sonnet 5 $0.00010 $0.00207
Haiku 4.5 $0.00005 $0.00103

Measured 10d ago against content hash 4e1ab3b5f62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

session-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.

templates/generated/skills/session-handoff/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Handoff

Attribution. This skill is adapted with permission from mattpocock/skills (MIT, © Matt Pocock). The original skill (handoff) was written to be lightweight and tool-agnostic. This Solo Orchestrator-adapted version writes to docs/handoffs/ so the handoff lives with the project as an auditable artifact (Solo's W7 handoff-readiness principle), and is named session-handoff to disambiguate from Solo's Phase 4 production HANDOFF.md (templates/generated/handoff.tmpl). See NOTICE for full attribution and license.

When to use

Use before any of:

  • Hard context-window break (the next reply might roll context out of memory).
  • Machine reboot or planned shutdown.
  • Switching to a different agent or operator mid-task.
  • End-of-day stop when work is mid-flight and you want to resume cleanly tomorrow.

Do not use this skill for:

  • Phase 4 production handoff to operations — that goes in HANDOFF.md via the project's existing templates/generated/handoff.tmpl. They are different artifacts with different audiences.
  • Single-task summaries inside a session — write those inline.

What it produces

Write a markdown document summarizing the current conversation so a fresh agent (or future-you) can continue cleanly. Save it to:

docs/handoffs/YYYY-MM-DD-<topic-slug>.md

(Create docs/handoffs/ if it does not exist.)

The handoff document MUST include:

  1. Where we are — one-paragraph status of the work in progress: current branch, current PR (if any), current task on the implementation plan, current test-gate state.
  2. What just shipped this session — bullet list of commits / PRs / artifacts produced. Link to file paths and PR URLs, do not duplicate content.
  3. What's blocked / waiting — anything paused on user review, external state (CI, deploys), or unanswered design questions.
  4. What's next — the specific next concrete action. If multiple options exist, list them with the recommendation.
  5. References — paths to PRDs, plans, ADRs, specs, TRIAGE docs, calibration reports the next session will need. Use repo-relative paths.
  6. Resume prompt — a single paragraph the user can paste into the next session (or have an agent re-enter with) that re-establishes context. Should be self-contained: "Continuing from handoff at . . ."

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file 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. 10d ago First seen · 66 lines · 51 tokens per session scan A 4e1ab3b5f62f

Subscribe to this mod's changes

session-handoff is a skill published in the GitHub repository kraulerson/solo-orchestrator (29 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,033 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 2026-08-30.