
Response Compression
Strip filler, hedging, and decorative bloat from agent replies to reclaim roughly 200–400 tokens per turn when context window pressure slows shipping.
Overview
Response Compression is a journey-wide agent skill that removes filler and framing from agent replies—usable whenever a solo builder needs to save context tokens before committing to more tool calls or code.
Install
npx skills add https://github.com/athola/claude-night-market --skill response-compressionWhat is this skill?
- Targets 200–400 tokens saved per response while preserving clarity
- Elimination rules for filler, hedging, hype words, and decorative emojis
- Before/after transformations and a quick-reference checklist
- Documented `alwaysApply: true` for persistent terse output
- Estimated skill footprint ~500 tokens; complexity tagged low in SKILL.md
- Documented savings: 200–400 tokens per response
- Estimated skill size: ~500 tokens
- Frontmatter: alwaysApply true
Adoption & trust: 1 installs on skills.sh; 304 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
Agent answers balloon with hedging and repetition, eating 200–400+ tokens per turn and pushing you toward context limits mid-ship.
Who is it for?
Power users in long agent sessions who already understand the task and want terse, checklist-friendly answers.
Skip if: First-time setup walkthroughs, teaching explanations, or stakeholders who need narrative context and reassurance language.
When should I use this skill?
Use when responses feel bloated or context is filling fast; compress verbose output per elimination rules.
What do I get? / Deliverables
Replies stay dense and factual with less decorative language, freeing hundreds of tokens per turn for code and commands.
- Shorter agent replies following elimination and directness guidelines
- Checklist-aligned answers without removed informational content
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Summarize competitor notes without emoji headers and hedge phrases burning context.
Keep implementation replies checklist-short while iterating on a feature branch.
Deliver review findings as direct bullets instead of long framing paragraphs.
Triage production issues with terse status lines during a long debugging session.
How it compares
Behavioral response policy skill—not a code formatter, test runner, or RAG compression tool.
Common Questions / FAQ
Who is response-compression for?
Solo builders and indie devs using Claude Code, Cursor, or similar agents who hit context limits because replies are unnecessarily verbose.
When should I use response-compression?
Across Idea research summaries, Validate scoping threads, Build implementation, Ship review notes, Launch copy drafts, Grow analytics Q&A, and Operate incident triage—whenever `alwaysApply` terse output helps and detailed pedagogy is not required.
Is response-compression safe to install?
It is instructions-only with no tools listed in frontmatter; still review the Security Audits panel on this Prism page before enabling `alwaysApply` in production workflows.
SKILL.md
READMESKILL.md - Response Compression
## Table of Contents - [Elimination Rules](#elimination-rules) - [Before/After Transformations](#beforeafter-transformations) - [Termination Guidelines](#termination-guidelines) - [Directness Guidelines](#directness-guidelines) - [Quick Reference Checklist](#quick-reference-checklist) - [Token Impact](#token-impact) - [Integration](#integration) # Response Compression Eliminate response bloat to save 200-400 tokens per response while maintaining clarity. ## When To Use - Reducing verbose output to save context tokens - Providing concise answers without losing information ## When NOT To Use - Educational explanations where detail improves understanding - First-time setup instructions needing step-by-step clarity ## Elimination Rules ### ELIMINATE | Category | Examples | Replacement | |----------|----------|-------------| | **Decorative Emojis** | `--` | (remove entirely) | | **Filler Words** | "just", "simply", "basically", "essentially" | (remove or rephrase) | | **Hedging Language** | "might", "could", "perhaps", "potentially", "I think" | Use factual statements | | **Hype Words** | "powerful", "amazing", "seamless", "robust", "elegant" | Use precise descriptors | | **Conversational Framing** | "Let's dive in", "Now that we've", "Moving forward" | Start with content | | **Transitions** | "Furthermore", "Additionally", "In conclusion" | (remove, use structure) | | **Call-to-Action** | "Feel free to", "Don't hesitate to", "Let me know if" | (remove from endings) | ### PRESERVE (When Appropriate) | Category | Example | When to Use | |----------|---------|-------------| | **Status Indicators** | `[pass] [fail] [warn]` | In structured output, checklists | | **Technical Precision** | Exact error messages | When debugging | | **Safety Warnings** | Critical info about data loss | Always preserve | | **Context Setting** | Brief necessary background | When user lacks context | ## Before/After Transformations ### Example 1: Opening Bloat **Before** (68 tokens): ``` Great question! I'd be happy to help you understand how this works. The bloat detector is a powerful tool that analyzes your codebase and provides comprehensive insights into potential issues... ``` **After** (28 tokens): ``` The bloat detector analyzes codebases using three tiers: quick scan (heuristics), static analysis (tools), and deep audit (git history). ``` ### Example 2: Closing Bloat **Before** (45 tokens): ``` I've completed the task. Here's what I did: - Deleted 5 files - Saved 18k tokens Next steps: 1. Review the changes 2. Run tests 3. Commit if satisfied Let me know if you need anything else! ``` **After** (15 tokens): ``` Done. Deleted 5 files, saved 18k tokens. Backup: backup/unbloat-20260102 ``` ### Example 3: Hedging Removal **Before**: ``` I think this might potentially be causing the issue, but I could be wrong. Perhaps we should consider looking into it further. ``` **After**: ``` This causes the issue. Investigate the connection pool timeout setting. ``` ## Termination Guidelines ### When to Stop End response immediately after: - Delivering requested information - Completing requested task - Providing necessary context ### Avoid Trailing Content | Pattern | Action | |---------|--------| | "Next steps:" | Remove unless safety-critical | | "Let me know if..." | Remove always | | "Summary:" | Remove (user has the response) | | "Hope this helps!" | Remove always | | Bullet recaps | Remove (redundant) | ### Exceptions (When Summaries Help) - Multi-part tasks with many changes - User explicitly requests summary - Critical rollback/backup information - Complex debugging with multip