Agent Skillsdiegosouzapw/OmniRoute › omni-compression

omni-compression

GitHub

配置RTK、Caveman及堆叠压缩模式,管理语言包与自定义规则,通过API透明压缩Token负载,降低60-90%成本。

skills/omni-compression/SKILL.md diegosouzapw/OmniRoute

Trigger Scenarios

需要降低LLM调用Token成本 配置或切换文本压缩引擎模式 查询或管理压缩语言包与规则

Install

npx skills add diegosouzapw/OmniRoute --skill omni-compression -g -y
More Options

Use without installing

npx skills use diegosouzapw/OmniRoute@omni-compression

指定 Agent (Claude Code)

npx skills add diegosouzapw/OmniRoute --skill omni-compression -a claude-code -g -y

安装 repo 全部 skill

npx skills add diegosouzapw/OmniRoute --all -g -y

预览 repo 内 skill

npx skills add diegosouzapw/OmniRoute --list

SKILL.md

Frontmatter
{
    "name": "omni-compression",
    "description": "Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%."
}

Overview

Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

POST /api/compression/preview

Preview compression for a message payload

curl -X POST https://localhost:20128/api/compression/preview \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/compression/language-packs

List Caveman compression language packs

curl https://localhost:20128/api/compression/language-packs \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/compression/rules

List Caveman compression rule metadata

curl https://localhost:20128/api/compression/rules \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

OmniRoute — Compression

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Overview

OmniRoute compresses token payloads before forwarding to providers. No code changes required — set it once, it applies to all requests transparently.

Engine Best for Typical savings
RTK Terminal / build / test / git output 60–90%
Caveman Human prose, chat history 46% input
Stacked (rtk → caveman) Mixed coding sessions 78–95%
MCP accessibility filter Browser/accessibility tool results 60–80%

Get current settings

curl $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY"

Enable RTK (best for coding agents)

curl -X PUT $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "mode": "rtk", "enabled": true }'

Enable stacked mode (maximum savings)

curl -X PUT $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "stacked",
    "enabled": true,
    "stackedPipeline": ["rtk", "caveman"]
  }'

Enable Caveman (prose / chat)

curl -X PUT $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "mode": "standard", "enabled": true }'

Caveman intensities: lite (safe), standard (balanced), aggressive (long sessions), ultra (context recovery).

Preview compression before enabling

curl -X POST $OMNIROUTE_URL/api/compression/preview \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "rtk",
    "text": "$ npm test\n> jest\n\nPASS src/a.test.ts (2.1s)\nPASS src/b.test.ts (1.8s)\n..."
  }'

Response includes compressed, original_length, compressed_length, savings_pct.

MCP accessibility-tree filter (browser agent use)

When OmniRoute is used with browser/Playwright MCP tools, it automatically compresses verbose accessibility-tree tool results. Enabled by default; configure thresholds:

curl -X PUT $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mcpAccessibility": {
      "enabled": true,
      "collapseThreshold": 30,
      "maxTextChars": 50000
    }
  }'

collapseThreshold: collapse sibling lines when ≥ N repeats (default 30).
maxTextChars: hard truncate after N chars with navigation hint (default 50000).

Language packs (Caveman)

Caveman supports language-aware rules for pt-BR, es, de, fr, ja:

curl -X PUT $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "standard",
    "cavemanConfig": {
      "language": "pt-BR",
      "autoDetectLanguage": true
    }
  }'

Via MCP

omniroute_compression_status     → current settings + savings analytics
omniroute_compression_configure  → update mode/threshold/language
omniroute_set_compression_engine → switch engine at runtime

Disable compression

curl -X PUT $OMNIROUTE_URL/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -d '{ "enabled": false }'

Errors

  • 400 invalid mode → use off, lite, standard, aggressive, ultra, rtk, or stacked
  • 400 invalid stackedPipeline → array must contain valid engine ids (rtk, caveman)

Version History

  • 1cafd32 Current 2026-07-25 11:47

Same Skill Collection

skills/cli-a2a/SKILL.md
skills/cli-backup-sync/SKILL.md
skills/cli-batches/SKILL.md
skills/cli-chat/SKILL.md
skills/cli-compression/SKILL.md
skills/cli-contexts/SKILL.md
skills/cli-cost-usage/SKILL.md
skills/cli-eval/SKILL.md
skills/cli-health/SKILL.md
skills/cli-keys/SKILL.md
skills/cli-mcp/SKILL.md
skills/cli-models/SKILL.md
skills/cli-plugins-skills/SKILL.md
skills/cli-policy-audit/SKILL.md
skills/cli-providers/SKILL.md
skills/cli-resilience/SKILL.md
skills/cli-routing/SKILL.md
skills/cli-serve/SKILL.md
skills/cli-setup/SKILL.md
skills/cli-skill-collector/SKILL.md
skills/cli-tunnel/SKILL.md
skills/config-codex-cli/SKILL.md
skills/omni-agents-a2a/SKILL.md
skills/omni-api-keys/SKILL.md
skills/omni-auth/SKILL.md
skills/omni-budget/SKILL.md
skills/omni-cache/SKILL.md
skills/omni-cli-tools/SKILL.md
skills/omni-combos-routing/SKILL.md
skills/omni-context-rtk/SKILL.md
skills/omni-db-backups/SKILL.md
skills/omni-github-skills/SKILL.md
skills/omni-inference/SKILL.md
skills/omni-mcp/SKILL.md
skills/omni-models/SKILL.md
skills/omni-providers/SKILL.md
skills/omni-proxies/SKILL.md
skills/omni-resilience/SKILL.md
skills/omni-settings/SKILL.md
skills/omni-sync-cloud/SKILL.md
skills/omni-tunnels/SKILL.md
skills/omni-usage-logs/SKILL.md
skills/omni-version-manager/SKILL.md
skills/omni-webhooks/SKILL.md
skills/ponytail/SKILL.md

Metadata

Files
0
Version
3d7ed7a
Hash
4f76b5aa
Indexed
2026-07-25 11:47

inicio - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-22 03:17
浙ICP备14020137号-1 $mapa de visitantes$