Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

cost-compact-context — Claude Code skill: context compaction

A skill that wraps getTokenOptimizer().getCompactContext() for token cost analysis. Retrieves compacted context from ReasoningBank, reports tokens saved via bridge measurements, and exposes agent-booster availability.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add ruvnet/ruflo --skill cost-compact-context -a claude-code
Open on GitHub

What cost-compact-context does

The skill takes your query and invokes the token optimizer from @claude-flow/integration. If agentic-flow is installed, you get a table with retrieved memories count, tokens saved (as reported by the bridge), agent-booster availability, and cache hit rate. If the package is absent, the skill exits cleanly and reports that the bridge is unavailable.

The script runs as a Node one-liner from within the v3/ directory so that @claude-flow/integration resolves correctly. It imports the canonical token-optimizer export (not dist/token-optimizer.js, which would duplicate the .js extension via Node's ./* exports rule), calls getCompactContext(query), and outputs markdown plus a JSON line via COMPACT_QUIET=1.

Token savings figures are a heuristic—query tokens minus compact prompt tokens—not a baseline-measured reduction. The skill carries this disclaimer: the numbers reflect what the bridge computes, not independent verification.

What it helps with

  • measure token savings from context compaction for a specific query
  • retrieve the list of memories that the optimizer can fetch
  • check if agent-booster is available in your setup
  • track cache hits when repeating queries

Example prompts for the agent

  • How many tokens will the optimizer save for a claude-flow integration query?
  • Show me compacted context and token stats for this RAG analysis
  • Check agent-booster availability and list cached memories

How to install cost-compact-context

1Skills CLI (Vercel)

npx skills add ruvnet/ruflo --skill cost-compact-context -a claude-code

2Manually: put the files in place

~/.claude/skills/cost-compact-context/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cost-compact-context/

From the same set104

The whole set →
ruflo ruvnet This skill adds multi-agent orchestration, memory, routing, and MCP tools to a project. Use it for swarm tasks and multi-step workflows. Claude Code CX Codex Cursor +1 4,000installs Swarm Orchestration ruvnet Skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. Claude Code CX Codex Cursor +1 2,100installs github-project-management ruvnet Turns issue triage and board upkeep into gh and ruv-swarm calls: labels, subtasks, duplicate lookup. Useful when the tracker holds more tickets than order. Claude Code CX Codex Cursor +1 1,400installs github-workflow-automation ruvnet Automates GitHub Actions with AI agent coordination. Generates optimised pipelines, manages pull requests, analyzes failed runs, and deploys updates with risk assessment. Claude Code CX Codex Cursor +1 1,300installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs stream-chain ruvnet Chains sequential agent steps together using streaming JSON flow and provides ready-to-run pipelines. Claude Code CX Codex Cursor +1 1,200installs flow-nexus-swarm ruvnet Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs performance-analysis ruvnet Detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. Claude Code CX Codex Cursor +1 1,200installs

Similar

skillify Yeachan-Heo Converts a successful multi-step workflow from your current session into a reusable skill draft with YAML frontmatter. Claude Code CX Codex Cursor +1 638installs computer-use-agents sickn33 Guides the architecture of AI agents that control screens, cursors, and keystrokes using Anthropic Computer Use or OpenAI Operator. Useful for sandboxed desktop and GUI automation. Claude Code CX Codex Cursor +1 959installs convex-create-component convex A skill to design and build reusable Convex components with isolated tables and a clear API boundary. Useful when you need to extract backend logic into a self-contained module or package an integration that owns its own data. Claude Code CX Codex Cursor +1 130,600installs debug Yeachan-Heo Diagnoses broken OMC sessions, workflow failures, and repo state issues using traces and targeted reproduction. Claude Code CX Codex Cursor +1 629installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. Claude Code CX Codex Cursor +1 410,700installs

Questions about cost-compact-context

How do I install cost-compact-context in Claude Code?

Run npx skills add ruvnet/ruflo --skill cost-compact-context -a claude-code. After installation, the skill is available at ~/.claude/skills/cost-compact-context/SKILL.md.

What does cost-compact-context do?

The skill calls the token optimizer from @claude-flow/integration, compacts context for your query, and reports tokens saved, which memories were retrieved, and whether agent-booster is available.

What happens if agentic-flow is not installed?

The skill outputs a message that the bridge is unavailable, returns zero savings (tokensSaved: 0), and exits cleanly without error.

Source text

SKILL.md · MIT 
---
name: cost-compact-context
description: Wrap getTokenOptimizer().getCompactContext() to retrieve compacted ReasoningBank context for cost-analysis queries; report bridge-reported tokensSaved
argument-hint: "<query>"
allowed-tools: Bash
---

# Cost Compact Context

Wraps `getTokenOptimizer().getCompactContext()` from `@claude-flow/integration` for cost-analysis queries. The bridge dynamically imports `agentic-flow` with graceful fallback: when the package isn't installed, `tokensSaved` is `0` and the skill exits cleanly. No MCP tool wraps `getTokenOptimizer` today (ADR-0002 §"Riskiest assumption"); we shell a Node one-liner instead.

## Steps

1. **Take the query** — the single argument.
2. **Invoke** — run from anywhere under `v3/` so `@claude-flow/integration` resolves:

   ```bash
   ( cd v3 && node ../plugins/ruflo-cost-tracker/scripts/compact.mjs "<QUERY>" )
   ```

   The script imports `@claude-flow/integration/token-optimizer` (canonical export — **not** `dist/token-optimizer.js`, which would double the `.js` extension via Node's `./*` exports rule), calls `getCompactContext(query)`, and prints a markdown summary plus a JSON line via `COMPACT_QUIET=1`.

3. **Report** — markdown table with: memories retrieved, tokens saved (bridge-reported), agentic-flow availability, cache hit rate. The script also emits a "bridge-reported, not measured against a no-RAG baseline" disclaimer. On bridge-unavailable: prints "agentic-flow not installed — bridge returns inert results." and exits cleanly.

## Caveats — claimed upstream, not yet verified

CLAUDE.md root claims `ReasoningBank retrieval: -32%` tokens. The bridge's `tokensSaved` is `query_tokens − compact_prompt_tokens` (token-optimizer.ts:141–143) — a heuristic, **not** a baseline-measured saving. token-optimizer.ts:9–10 itself says: *"No fabricated metrics are reported — all stats reflect real measurements"*. This skill carries that disclaimer forward.

Booster-specific availability is **not** exposed as a getter — observable only through `optimizedEdit()` returning `method: 'agent-booster'`. The canonical Tier 1 signal is `[AGENT_BOOSTER_AVAILABLE]` (see `cost-booster-route`).

## Fallback

`agentic-flow` not installed → `getCompactContext` returns `{tokensSaved: 0, memories: []}` (line 116–124), `optimizedEdit` returns `{method: 'traditional'}`, `getOptimalConfig` falls back to anti-drift defaults. Skill exits cleanly with the "not available" message.

## Cross-references

ADR-0002 Decision #2 + §"Riskiest assumption" · `token-optimizer.ts:308` (singleton export) · `docs/benchmarks/0002-baseline.md` (verification findings).

© ruvnet · MIT · ruvnet/ruflo

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor