handoff

A handoff summary that records important decisions, predictions, surprises, mistakes, and unusual details from an agent session.

In plain words
What is it for?
Use it to prepare a concise record for the next session or agent, especially before clearing or compacting the conversation.
Why use it?
It preserves useful context that could otherwise be lost when a conversation is cleared or shortened.

Skill for Claude CodeCodex

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/rakovi4/continue-framework/handoff
Any agent
npx skills add rakovi4/continue-framework --skill handoff
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 846 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 $0.00080 $0.00846
Opus 5 $0.00040 $0.00423
Sonnet 5 $0.00016 $0.00169
Haiku 4.5 $0.00008 $0.00085

Measured 3d ago against content hash 29c1cf772fc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

.claude/skills/handoff/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff - Preserve Conversation Context

Run this to persist what a future session would otherwise lose. /handoff runs automatically the moment the agent observes something worth noting during work, and manually before /clear or /compact as a final sweep. /handoff is the ONLY writer of journey summaries and carryover.

Workflow

  1. Identify the work item -- find the story or task the conversation worked on (recent git log Story N / Task N, or the progress.md that changed). Resolve its folder.
  2. Locate the last work-unit commit -- the conversation since that commit is the review window. Everything after it (discussion, debugging, decisions) is what /handoff captures; the work unit itself is already recorded in progress.md and its commit.
  3. Review the window against the "When to Write" triggers in .claude/templates/workflow/summary-format.md. Decide, per trigger, whether anything noteworthy happened.
  4. Write entries, or nothing -- if at least one trigger fired, append entries to the summary file (see File Layout) in the strict format from .claude/templates/workflow/summary-format.md. Before appending, check the file for an entry already covering the same moment and skip it -- /handoff runs many times per conversation and must not duplicate. If nothing fired, or every fired trigger is already recorded, create no file and append no line -- report "nothing to record".
  5. Promote carryover -- if a scenario's last step is now [x] (scenario complete), promote codebase-quirk and system-invariant entries from that scenario's summary to carryover.md at the story root, each with a From: scenario N (slug) backreference. Tasks have no carryover.
  6. Report -- list each file touched and each entry appended (or "nothing to record"), then tell the user it is safe to /clear.

File Layout

Work item Summary file Carryover
Story scenario ProductSpecification/stories/NN-story-name/summaries/{scenario-slug}.md ProductSpecification/stories/NN-story-name/carryover.md
Task ProductSpecification/tasks/N-type-slug/summary.md none

Read the full file on GitHub · 38 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. 3d ago First seen · 38 lines · 80 tokens per session scan A 29c1cf772fc3

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 846 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens