A conversation handoff helper that turns a long chat into a short summary for a new conversation. The handoff records the goal, decisions, current state, next step, and important constraints.

Use it when a conversation becomes slow or forgetful, reaches a usage limit, or you want to start over without losing key details.

Long chats use more context and can make earlier details harder to recall. A compact handoff lets you continue in a fresh chat with less repeated history.

fresh-start — Skill for Claude Code by egorfedorov

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 egorfedorov/claude-context-optimizer --skill fresh-start

Clone the repo

git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer

Made for: Claude Code.

Or install context-optimizer, the plugin that ships this one along with the rest of its 27 skills, 3 agents, 6 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/fresh-start/github.svg)](https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/fresh-start)

Your own site

<a href="https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/fresh-start"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/fresh-start/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/egorfedorov/claude-context-optimizer/fresh-start"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/fresh-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 469 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	$0.00060	$0.00469
Opus 5.5	$0.00024	$0.00188
Sonnet 5.5	$0.00012	$0.00094
Haiku 4.5	$0.00006	$0.00047

Measured today against content hash 44c72ef3c833, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fresh-start 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 today.

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/fresh-start/SKILL.md · 46 lines

What it actually says

Fresh start

Every message re-sends the whole conversation, so a long one uses up limits fast and recalls its early details worse. A new conversation that starts from a short handoff costs a fraction and stays sharp.

When to offer it

The user asks to start over, hits a limit, or says replies got slow or forgetful.
The conversation is clearly long: many long turns, large pasted files or documents. Offer it once, in one sentence, at a natural break. Don't interrupt a short conversation or a task that is nearly done.

The handoff

Write it in the user's language, under 300 words, inside one code block so it copies cleanly:

Goal — one line.
Decisions so far — bullets, each with its reason in a few words.
Current state — what exists now: files, drafts, versions, results. Quote only short snippets that the next step needs; name everything else.
Next step — the very next thing to do, then any open questions.
Must not be lost — names, numbers, constraints, preferences, things that were tried and failed.

Then tell the user: open a new conversation, paste the block, and continue.

On each surface

claude.ai chat: a new chat with the pasted handoff. In a Project, the project's files stay available, so the handoff can just name them.
Cowork: start a new task with the handoff as its first message.
Claude Code: /compact keeps working in place and is usually enough. For a clean break, /clear and paste the handoff. /cco-task patch keeps structured task state across /compact automatically.

Never paste whole files, logs or the transcript into the handoff.

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.

today First seen · 46 lines · 60 tokens per session scan A 44c72ef3c833

Subscribe to this mod's changes

fresh-start is a skill published in the GitHub repository egorfedorov/claude-context-optimizer (116 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 469 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.

Memory and context Productivity ai-tools anthropic claude-code-plugin cli-plugin context-management

alive-morning

Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.

alivecontext/alive · 24 tokens

alive:save

The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…

alivecontext/alive · 78 tokens

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

nav-compact

Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.

qf-studio/navigator · 38 tokens

alive:capture-context

Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…

alivecontext/alive · 74 tokens

alive:load-context

The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…

alivecontext/alive · 81 tokens