agentleFS
vikas8520-codervikas8520-coder/nerve/skills/omni-compression/SKILL.md

omni-compression

Skill0 starsChanged 3 months agoMITView on GitHub

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

  • Reads credentials
  • Sends data out

3 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All requests require a valid Bearer token or session cookie.

    line 13
  2. Very specific:

    When Nerve is used with browser/Playwright MCP tools, it automatically compresses verbose accessibility-tree tool results.

    line 124

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->

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 $NERVE_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 $NERVE_TOKEN"

GET /api/compression/rules

List Caveman compression rule metadata

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

Payloads

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

<!-- skill:custom-start --><!-- Migrated from skills/nerve-compression/SKILL.md (preserved curated content) -->

Nerve — Compression

Requires NERVE_URL and NERVE_KEY. See entry-point SKILL for setup.

Overview

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

EngineBest forTypical savings
RTKTerminal / build / test / git output60–90%
CavemanHuman prose, chat history46% input
Stacked (rtk → caveman)Mixed coding sessions78–95%
MCP accessibility filterBrowser/accessibility tool results60–80%

Get current settings

curl $NERVE_URL/api/settings/compression \
  -H "Authorization: Bearer $NERVE_KEY"

Enable RTK (best for coding agents)

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

Enable stacked mode (maximum savings)

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

Enable Caveman (prose / chat)

curl -X PUT $NERVE_URL/api/settings/compression \
  -H "Authorization: Bearer $NERVE_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 $NERVE_URL/api/compression/preview \
  -H "Authorization: Bearer $NERVE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "rtk",
    "text": "$ 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 Nerve is used with browser/Playwright MCP tools, it automatically compresses verbose accessibility-tree tool results. Enabled by default; configure thresholds:

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

Via MCP

nerve_compression_status     → current settings + savings analytics
nerve_compression_configure  → update mode/threshold/language
nerve_set_compression_engine → switch engine at runtime

Disable compression

curl -X PUT $NERVE_URL/api/settings/compression \
  -H "Authorization: Bearer $NERVE_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)
<!-- skill:custom-end -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.