More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Tokenlean: answers first, no filler, fewer tokens

    2

    Strips filler from agent replies and adds compression modes you switch on by name. Measured on real session logs: about 10% fewer output tokens on average.

    Free

    1 useSecurity scanned
    Tokenlean: answers first, no filler, fewer tokens

    Tokenlean: answers first, no filler, fewer tokens

    Example session with this skill installed

    jimat penuh: explain the current project structure and what needs refactoring in the auth module.

    • Read your context and instructions
    • Compiled the tokenlean

    ✅ jimat penuh active: fragments + tables.

    Project Structure & Auth Refactor

    ComponentPathStatus
    Entrysrc/index.tsLean; no changes
    Auth Logicsrc/lib/auth.tsRefactor needed: 800+ LOC, mixed concerns
    Middlewaressrc/middleware/Redundant JWT checks; consolidate

    Auth Refactor Targets

    • Logic split Move session validation to session.ts.
    • Secret handling Replace hardcoded strings with env schema.
    • Error mapping Standardize HTTP 401/403 responses.

    Next steps
    Extract auth.ts logic into sub-modules.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    You are paying for tokens you do not need. Every "Certainly! I'd be happy to help" and verbose code explanation drains your API budget and hits rate limits faster. This skill enforces strict token economy through structural rules and graduated compression modes.

    What it does

    • Filler removal Strips all conversational preamble, postamble, and polite social padding from agent replies.
    • Graduated compression Toggles between three intensity levels (ringan, penuh, ultra) to control sentence density and fragment usage.
    • Dry modes Provides dry and answer-only settings for zero-narrative, deliverable-exclusive outputs.
    • Agentic optimization Implements logic for batching subagent tasks and extracting data before fan-out to prevent context bloat.
    • Durable state management Directs agents to store intermediate results on disk rather than re-reading large files in every turn.

    How it works

    1. Toggle persistence Use jimat on, jimat penuh, or jimat ultra to set a session-wide compression level.
    2. Per-message override Prefix a single prompt with /jimat or /dry to compress one specific response without changing global settings.
    3. Automated extraction The agent applies extraction rules to logs and dumps before passing them to subagents or parallel pipelines.
    4. Deactivation Use jimat off to return to the default discipline of no-filler prose.

    Frameworks & tools

    This skill is framework-agnostic. It is optimized for Claude Code, Cursor, and any LLM agent performing high-volume coding or data extraction tasks where output length impacts cost or speed.

    Why this beats prompting it yourself

    Writing "be concise" in a system prompt is easily ignored by modern LLMs during complex reasoning. This skill provides a measured logic for structural density and specific agentic patterns like batching and extraction that simple prompts miss.

    Use cases

    • API cost reduction Cutting output tokens on long replies: about 16% fewer at P90 in measured session logs.
    • Massive log analysis Extracting load-bearing data points before fanning out to subagent pipelines.
    • Rate limit management Staying under usage tiers during heavy refactoring sessions or parallel test generation.
    • Emergency conservation Switching to ultra mode when approaching daily context window limits.

    Known limitations

    Does not compress code blocks, file paths, or security warnings to ensure technical accuracy. Performance is best on long-form replies rather than short one-liners.

    Does not compress code, file paths, or security warnings. Savings are concentrated on long-tail replies, not short answers. Requires manual triggers for specific compression levels.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed29 days ago
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    Tokenlean cuts output tokens (and with them cost and rate-limit pressure) by stripping conversational filler and using structural compression logic that is more resilient than simple "be concise" prompts.

    This skill is framework-agnostic and optimized for high-volume coding environments like Claude Code, Cursor, and custom agentic pipelines where output length directly impacts performance.

    The "ultra" mode uses maximum sentence density and fragment logic, while "dry" mode eliminates all narrative entirely, delivering only code blocks or specific data requested.

    No, the skill is specifically engineered to protect the integrity of code blocks, file paths, and security warnings, ensuring that only the surrounding prose and meta-talk are compressed.

    You receive the full logic set for all three compression tiers, the "dry" and "answer-only" modules, and the agentic batching protocols for managing subagent workflows.

    Yes, Tokenlean includes durable state management instructions that teach your agent to store and reference intermediate data on disk, preventing costly re-reads of large files.

    New in LLM Ops