Is the Continue (Token Saver) skill free?

Yes. The skill itself is free from ww-w-ai/claude-code-token-saver. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Continue (Token Saver) SkillProof Score?

7.6/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Continue (Token Saver)?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Continue (Token Saver) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Continue (Token Saver)

Zero-token session context restore by reading transcripts directly, not /compact

by ww-w-ai · ww-w-ai/claude-code-token-saver

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 20, 2026 · 7654983

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 17, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran the bundled list-sessions.js and preprocess.js live against a real 19MB project transcript: it detected the auto-compact boundary and built a verbatim compact cache in under two seconds with zero LLM tokens, a genuine alternative to /compact. But the skill is plugin-shaped: SKILL.md invokes its scripts via ${CLAUDE_PLUGIN_ROOT}/scripts/, which a plain skill-directory install does not provide, so the exact command fails with 'Cannot find module /scripts/list-sessions.js'. It works well installed as the plugin (/plugin install claude-code-token-saver@ww-w-ai) but is broken as a standalone skill copy. Mislabeled crypto; it is an efficiency/token-saving tool.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 3/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Continue (Token Saver) does

Restores context from previous Claude Code sessions by parsing the JSONL transcripts directly, with no LLM summarization call. Triggers on 'continue', 'restore context', 'pick up where I left off', 'what was I doing'. A cheaper, faster alternative to /compact for resuming prior work.

How to install Continue (Token Saver)

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Continue (Token Saver)

/continue Zero-token session context restore by reading transcripts directly, not /compact

It also activates on plain-language prompts like these:

What was I doing in my last session? Pick up where I left off
Restore my previous context without burning a bunch of tokens
Continue from where we stopped yesterday on this project

Frequently asked questions

Is the Continue (Token Saver) skill free?: Yes. The skill itself is free from ww-w-ai/claude-code-token-saver. SkillProof publishes the install command and an independent test verdict at no cost.
Does Continue (Token Saver) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Ran the bundled list-sessions.js and preprocess.js live against a real 19MB project transcript: it detected the auto-compact boundary and built a verbatim compact cache in under two seconds with zero LLM tokens, a genuine alternative to /compact. But the skill is plugin-shaped: SKILL.md invokes its scripts via ${CLAUDE_PLUGIN_ROOT}/scripts/, which a plain skill-directory install does not provide, so the exact command fails with 'Cannot find module /scripts/list-sessions.js'. It works well installed as the plugin (/plugin install claude-code-token-saver@ww-w-ai) but is broken as a standalone skill copy. Mislabeled crypto; it is an efficiency/token-saving tool.
What is the Continue (Token Saver) SkillProof Score?: 7.6/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Continue (Token Saver)?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Continue (Token Saver) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.