Save Tokens

Organization

aspenkit

save-tokens

Token-saving session automation — statusline, prompt guard, precompact handoffs, session rotation, and handoff commands for Claude Code

Overview

Publisher	aspenkit
Repository	`aspens`
Skill name	`save-tokens`
Stars	102
Forks	7
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by aspenkit on GitHub. Read the source before you install it.

Installation

Install the Save Tokens AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/aspenkit/aspens/tree/main/.agents/skills/save-tokens
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/aspenkit/aspens.git /tmp/aspens
mkdir -p .claude/skills
cp -r /tmp/aspens/.agents/skills/save-tokens .claude/skills/save-tokens

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Save Tokens in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Save Tokens on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Save Tokens is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

You are working on save-tokens — the feature that installs Claude Code hooks and commands to warn about token usage, auto-save handoffs before compaction, and support session rotation.

Domain purpose

aspens save-tokens installs three Claude Code hooks (statusline, prompt-guard, precompact) plus /save-handoff, /resume-handoff-latest, and /resume-handoff slash commands. The hooks observe Claude's own token telemetry and inject system messages telling Claude to rotate sessions before context blow-up. Handoff files persist enough state in .aspens/sessions/ to resume seamlessly in a fresh session.

Business rules / invariants

Claude-only feature. Hooks and statusline only work with Claude Code; Codex has no save-tokens integration. Config lives in .aspens.json under saveTokens.
Config thresholds default 175k warn / 200k compact. Number.MAX_SAFE_INTEGER is the disabled sentinel for either threshold; target.js#isValidSaveTokensConfig() validates shape, types, and threshold ordering — invalid config causes readConfig() to return null.
writeConfig preserves feature config — saveTokens is preserved across writeConfig calls unless explicitly set to null.
Sessions dir gitignored — .aspens/sessions/.gitignore excludes everything except .gitignore and README.md.
Settings backup — first install creates .claude/settings.json.bak if settings exist and no backup exists yet.
StatusLine pre-existence guard — canInstallSaveTokensStatusLine() refuses to overwrite an unrelated custom statusLine.command; when refused, applyStatusLineAvailability() forces both thresholds to MAX_SAFE_INTEGER and disables sessionRotation.

Non-obvious behaviors

Three hook entry points dispatched by subcommand. Shell wrappers (*.sh) read stdin, resolve project dir, and call save-tokens.mjs with statusline, prompt-guard, or precompact. ASPENS_PROJECT_DIR env var overrides CLAUDE_PROJECT_DIR; both fall back to cwd.
Statusline doubles as telemetry recorder. recordClaudeContextTelemetry() writes .aspens/sessions/claude-context.json summing input_tokens + cache_creation_input_tokens + cache_read_input_tokens + output_tokens from context_window.current_usage. Telemetry older than 5 minutes is ignored by the prompt guard.
Prompt-guard speaks to Claude, not the user. Above compactAtTokens: saves a handoff (reason rotation-threshold if sessionRotation, else compact-threshold) and stdout-prints an "IMPORTANT — you must tell the user" block instructing fresh session + /resume-handoff-latest. Above warnAtTokens: suggests /save-handoff. When telemetry is missing, prints a one-time link to the aspens issues page.
Precompact hook only fires when saveHandoff is enabled and claude.enabled !== false; reason is precompact.
extractSessionFacts() parses the JSONL transcript to extract originalTask (first user message, 500 char cap), recentPrompts (last 3, 200 char cap each), filesModified (Edit/Write tool_use file_path), gitCommits (regex on Bash git commit -m "..."), and branch (from gitBranch on user records). Transcript path is validated to be inside projectDir; falls back to input.prompt when transcript is missing or outside the project.
Transcript parsing is best-effort — all errors caught, invalid JSON lines silently skipped; returns empty facts on failure.
pruneOldHandoffs() keeps newest 10 *-handoff.md files by lexicographic (timestamp) sort; older are unlinked. latestHandoff() uses the same sort.
--recommended install is non-interactive — used standalone or invoked by doc init --recommended (which also installs agents and the doc-sync git hook).
--remove cleans legacy artifacts too — removes both .sh and historic .mjs variants of each hook, plus the legacy save-tokens-resume.md command; strips statusLine if it points at save-tokens and filters any hook entry whose command contains save-tokens-; nulls saveTokens in .aspens.json.

Critical files (purpose, not inventory)

src/commands/save-tokens.js — install/remove orchestration; interactive multiselect (warnings, handoffs), --recommended, --remove. Exports installSaveTokensRecommended() consumed by doc-init.js.
src/lib/save-tokens.js — config + settings + template content builders (DEFAULT_SAVE_TOKENS_CONFIG, buildSaveTokensConfig, buildSaveTokensSettings, buildSaveTokensGitignore, buildSaveTokensReadme, buildSaveTokensRecommendations).
src/templates/hooks/save-tokens.mjs — runtime library: runStatusline, runPromptGuard, runPrecompact, saveHandoff, extractSessionFacts, telemetry record/read, handoff pruning, main() subcommand dispatch.
src/templates/hooks/save-tokens-{statusline,prompt-guard,precompact}.sh — shell wrappers; resolve PROJECT_DIR via cd "$SCRIPT_DIR/../.." && pwd and exec the .mjs with the matching subcommand.
src/templates/commands/{save-handoff,resume-handoff-latest,resume-handoff}.md — slash command bodies installed under .claude/commands/.

Critical Rules

Settings merge uses mergeSettings() from skill-writer.js — save-tokens hooks are treated as aspens-managed; do not hand-edit .claude/settings.json to add/remove save-tokens entries.
Hooks write to stdout to inject into Claude's context — comments in runPromptGuard() flag this; keep those messages addressed to Claude ("Tell the user...") not to a human reader.
Token sum includes cache tokens — do not switch to just input_tokens + output_tokens; that under-counts Claude's effective context use.

References

Impact integration: src/lib/impact.js — evaluateSaveTokensHealth() validates installed state

Last Updated: 2026-05-11

Frequently asked questions

What does the Save Tokens AI skill do?

Token-saving session automation — statusline, prompt guard, precompact handoffs, session rotation, and handoff commands for Claude Code

Why use Save Tokens on TypingMind?

Because you install it once and use it with any model. Save Tokens is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Save Tokens in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aspenkit/aspens/tree/main/.agents/skills/save-tokens. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Save Tokens?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Save Tokens?

As many as you like. As long as a model supports skills, you can use Save Tokens with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Save Tokens AI skill free?

Yes. It is published on GitHub by aspenkit under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Claw Score

openclaw

OrganizationPopular

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Control Ui E2e

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Domain purpose

Business rules / invariants

Non-obvious behaviors

Critical files (purpose, not inventory)

Critical Rules

References

Frequently asked questions

Related AI Skills

Set up your own AI workspace now