context-slimmerAudit and slim down always-loaded context files (AGENTS.md, TOOLS.md, USER.md, MEMORY.md, HEARTBEAT.md, SOUL.md, IDENTITY.md). Use when asked to reduce token usage, audit context files, optimize context window, or slim down workspace files. Measures current token cost and identifies what to move, remove, or compress.
Install via ClawdBot CLI:
clawdbot install SunDevilATB/context-slimmerAudit workspace files that load into every message and reduce their token footprint.
# Measure current context cost
bash scripts/measure.sh
# Full audit (outputs recommendations)
bash scripts/measure.sh --audit
For each always-loaded file, evaluate:
| File | Target |
|------|--------|
| AGENTS.md | < 500 tokens |
| TOOLS.md | < 500 tokens |
| USER.md | < 700 tokens |
| MEMORY.md | < 400 tokens |
| HEARTBEAT.md | < 400 tokens |
| SOUL.md | < 250 tokens |
| IDENTITY.md | < 50 tokens |
| Total | < 2,800 tokens |
Report: current size, projected size, savings per file. Include specific recommendations grouped by move/remove/compress.
Generated Mar 1, 2026
A team building AI agents needs to optimize token usage to reduce costs and improve response times. This skill helps audit always-loaded context files, identifying redundant or verbose content to slim down, ensuring efficient use of context windows in production environments.
Large organizations deploying AI agents for customer service or internal automation require cost-effective token management. This skill audits context files to remove outdated info and compress instructions, aligning with lean targets to minimize operational expenses while maintaining performance.
A startup developing an AI-powered tool needs to keep context files minimal to scale affordably. This skill provides recommendations to move task-specific content to on-demand skills, remove duplicates, and compress explanations, helping meet tight token budgets during rapid iteration.
R&D labs experimenting with AI agents require flexible context optimization for varied projects. This skill audits files like MEMORY.md and SOUL.md to eliminate repetition and streamline protocols, enabling efficient testing and adaptation of agent behaviors across different use cases.
Offer this skill as part of a subscription-based AI optimization platform. Users pay monthly for access to auditing tools, automated recommendations, and updates, generating recurring revenue from teams needing ongoing context management to control token costs.
Provide expert consulting to audit and slim context files for clients. Charge per project or hourly for personalized recommendations, move/remove/compress actions, and training, catering to enterprises with complex AI deployments seeking hands-on optimization.
Release a free basic version of the skill for measuring token costs, with premium features like detailed audits and automated slimming. Upsell to paid plans for advanced analytics and integration support, attracting a broad user base and converting power users.
💬 Integration Tip
Integrate this skill early in the development cycle to establish lean context habits; use the provided scripts for quick audits and align with target file sizes to avoid token bloat as projects scale.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection