Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Compress responses to reduce context usage by 30-50% · wasabeef | DecimalAI

agent toolingby wasabeef

Compress responses to reduce context usage by 30-50%

wasabeef/compress-responses-to-reduce-context-usage-by-30-50

Source wasabeef/claude-code-cookbook ↗License Not recorded

Compress responses to reduce context usage by 30-50%. Trigger with "token efficient mode", "compress responses", "save context", "save tokens".

SkillScore77Maintained

Automatic

AI Engineer pack

Last verified 8/15/2026

What it changes

Passed 17 of 22 test cases with the skill, and 4 of 22 without it.

Without skill18%

With skill77%

Checks it passed that the model alone missed

The response uses the rollback symbol ←.
The response uses validation shorthand val.
The response uses logic symbols like → or ∴.

and 18 more in the full report

13 fixed4 passed either way5 still failing0 broke

Pass-rate lift: +59 pp
Tokens: +72%
Agent turns: 0%
Response time: -33%

Model gemini-3.6-flashMeasured 8/15/2026v117 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/wasabeef-compress-responses-to-reduce-context-usage-by-30-50/SKILL.md https://app.decimal.ai/s/wasabeef-compress-responses-to-reduce-context-usage-by-30-50/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-compress-responses-to-reduce-context-usage-by-30-50, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/wasabeef-compress-responses-to-reduce-context-usage-by-30-50/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-compress-responses-to-reduce-context-usage-by-30-50

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/wasabeef-compress-responses-to-reduce-context-usage-by-30-50/SKILL.md https://app.decimal.ai/s/wasabeef-compress-responses-to-reduce-context-usage-by-30-50/SKILL.md

Raw file: /s/wasabeef-compress-responses-to-reduce-context-usage-by-30-50/SKILL.md ↗ · machine-readable summary at /s/wasabeef-compress-responses-to-reduce-context-usage-by-30-50.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

Summarize findings for PR #402 across `/src/auth/`, `/src/api/`, and `/src/utils/` in concise token-saving mode.

What was checked, without and with the skill
Checked	Without skill	With skill
The response lists file paths alongside domain and status symbols.	Missed	Passed
The response uses shorthand like auth, err, or qual.	Missed	Passed

case-11 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md242 linessingle file

Compress responses to reduce context usage by 30-50%

Reduces AI response context usage by 30-50% through compression efficiency mode.

Compress responses to reduce context usage by 30-50%

Token Efficiency Mode leverages visual symbols and abbreviation systems to compress Claude's responses. Generated code quality and content remain unchanged. Only the explanation method changes.

Usage

# Enable mode
"Respond in Token Efficiency Mode"
"--uc mode"
"Concise mode"

How It Works

1. Symbol System

Logic & Flow

Symbol	Meaning	Example
→	leads to, causes	`auth.js:45 → 🛡️ security risk`
⇒	converts to	`input ⇒ validated_output`
←	rollback, revert	`migration ← rollback`
⇄	bidirectional	`sync ⇄ remote`
&	and, combine	`🛡️ security & ⚡ performance`
\|	or, separator	`react\|vue\|angular`
:	define, specify	`scope: file\|module`
»	then, sequence	`build » test » deploy`
∴	therefore	`tests ❌ ∴ code broken`
∵	because	`slow ∵ O(n²) algorithm`

Status & Progress

| Symbol | Meaning | Usage |

Track record

Benchmark

17 / 22

test cases passed, vs 4 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

wasabeef / claude-code-cookbook

plugins/en/skills/token-efficient/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Compress responses to reduce context usage by 30-50%

Compress responses to reduce context usage by 30-50%

Usage

How It Works

1. Symbol System

Logic & Flow

Status & Progress

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills