agentleFS
Sign inStart free
cwinvestmentscwinvestments/memstack/skills/compress/SKILL.md

compress

Skill425 starsChanged 5 months agoMITView on GitHub

Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.

17 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use caveman-review, caveman-commit and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • huangzidaSkill

    caveman-review

    Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

    Also in 3 projects that use this

  • huangzidaSkill

    caveman-commit

    Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

    Also in 3 projects that use this

  • MicrosoftSkill

    caveman

    Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill activates, output:

    line 13
  2. Distinctive:

    Contextual: When user asks about token usage, context window limits, or session cost

    line 20
  3. Distinctive:

    If nothing is listening, start it:

    line 71

“Common” is measured: kept by at least 6 in 10 of the 13 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

Compress - TokenStack Proxy Manager

Monitor and troubleshoot the built-in TokenStack compression proxy for CC sessions.

Activation

When this skill activates, output:

Compress - Checking TokenStack status...

Then execute the protocol below.

  • Keywords: tokenstack, compression stats, token savings, proxy status, check proxy
  • Contextual: When user asks about token usage, context window limits, or session cost
  • Level: 2 (explicit trigger only)

Context Guard

ContextStatus
User says "tokenstack", "compression stats", "check proxy"ACTIVE - run status check
User asks about token savings or context windowACTIVE - point to dashboard report
Proxy errors or API connection failures appearACTIVE - run health diagnostics
General discussion about CC featuresDORMANT - do not activate
User is actively coding (no proxy issues)DORMANT - do not activate

What It Does

TokenStack is a transparent proxy between Claude Code and the Anthropic API. It compresses tool output before it reaches the API, extending effective context and lowering token cost.

This skill checks that the proxy is running and routing, and troubleshoots connection issues. For the full feature overview, enable steps, and transform tables, use the Token Optimization skill.

Prerequisites

TokenStack ships inside the memstack-skill-loader package. There is no separate install.

  • Start with the dashboard (recommended): python -m memstack_skill_loader dashboard --with-proxy
    • Starts the proxy on 127.0.0.1:8787 and sets ANTHROPIC_BASE_URL automatically.
  • Run only the proxy: python -m memstack_skill_loader proxy

Workflow

1. Health Check

curl http://127.0.0.1:8787/health

A healthy proxy responds on /health. If there is no response, the proxy is not running.

Note: the proxy has no /stats endpoint. Live savings are reported in the dashboard, not over curl. See "Reading Savings" below.

2. Confirm Routing

Open the dashboard and look at the proxy indicator. A live PRO or FREE badge means Claude Code traffic is routing through TokenStack. If the badge reads "not detected," the dashboard was started without --with-proxy; restart it with the flag.

3. Diagnose "not running"

Check the port:

netstat -ano | findstr 8787

If nothing is listening, start it:

python -m memstack_skill_loader dashboard --with-proxy

4. Reading Savings

Savings live in the dashboard (default http://localhost:3333):

  • Proxy indicator: PRO or FREE badge with session and 30-day percentages
  • Overview header: session and lifetime tokens saved
  • Burn Report: per-transform breakdown, estimated cost, time filters (all-time, daily, weekly, monthly), and a per-agent split for the Manager, Builder, and Reviewer

Tier Behavior

TierTransforms
FreeSix lossless text reductions, always applied
ProAdds seven transforms including AST truncation (license-gated)

A valid Pro license switches the proxy to Pro tier automatically. The dashboard badge shows the active tier.

Troubleshooting

SymptomFix
No response on /healthProxy not running. Start with python -m memstack_skill_loader dashboard --with-proxy.
Proxy indicator shows "not detected"Dashboard was started without --with-proxy. Restart with the flag.
Badge shows FREE but you hold ProLicense cache may be stale. The proxy revalidates the license on next start.
Cost figures differ from Anthropic ConsoleEstimates use list token prices and do not model server-side prompt caching. For billed cost, check console.anthropic.com.

Output Format

TokenStack Status
  Proxy: Running on :8787
  Tier: PRO
  Savings: read in the dashboard (Overview header and Burn Report)

Integration

  • Dashboard: proxy indicator, Overview header, and Burn Report
  • CC sessions: auto-routed when the dashboard is started with --with-proxy
  • Standalone proxy: python -m memstack_skill_loader proxy

Relationship to Other Skills

SkillScopeWhen to Use
Token OptimizationFull TokenStack overview, enable steps, transform tablesUnderstanding or turning on compression
Compress (this)Health, routing, troubleshootingProxy not running or not routing

Level History

  • Lv.1 - Base: health check and stats reporting for the legacy Headroom proxy. (Origin: MemStack, Feb 2026)
  • Lv.2 - Rewrite: retargeted to the built-in TokenStack proxy. Removed the external Headroom install and the /stats curl; savings are now read from the dashboard. (Jun 2026)

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.

Check your setup, free