Cost Compact Context
- 637 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
cost-compact-context is a Claude Code skill that wraps getTokenOptimizer().getCompactContext() from @claude-flow/integration to return compacted ReasoningBank context and report tokensSaved for developers who need cheape
About
cost-compact-context is a Bash-driven Claude Code skill in ruvnet/ruflo that shells a Node one-liner to call getTokenOptimizer().getCompactContext() from @claude-flow/integration when no MCP tool wraps getTokenOptimizer (noted in ADR-0002). The bridge dynamically imports agentic-flow with graceful fallback: if the package is missing, tokensSaved is 0 and the skill exits cleanly. Developers pass a single query argument and receive compacted ReasoningBank context sized for cost-analysis questions while seeing bridge-reported token savings. Reach for cost-compact-context when tuning Claude-Flow or agentic-flow agent runs where verbose reasoning context inflates billable tokens. It complements token optimizers and ReasoningBank workflows rather than replacing full context dumps or MCP-based inspection tools.
- cost-compact-context
Cost Compact Context by the numbers
- 637 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #604 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill cost-compact-contextAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 637 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you compact ReasoningBank context for token savings?
Use cost-compact-context for development tasks
Who is it for?
Developers running Claude-Flow or agentic-flow agents who need compact context and visible token savings on cost-analysis queries.
Skip if: Teams that require full uncompressed reasoning traces or already expose getTokenOptimizer through a dedicated MCP server wrapper.
When should I use this skill?
The user asks for compact agent context, ReasoningBank summaries, or token-cost analysis during Claude-Flow or agentic-flow development.
What you get
Compacted ReasoningBank context payload and a tokensSaved count from the optimizer bridge.
- Compacted ReasoningBank context
- tokensSaved metric
Files
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:
( 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).
Related skills
Lark Openapi ExplorerInstantly explore, test, and generate calls against the full Lark (Feishu) OpenAPI surface without leaving their agent workflow.493k
Lark EventConsume real-time events from Lark/Feishu as structured NDJSON streams inside AI agent workflows.387k16kLark Openapi ExplorerWhen an existing Lark/Feishu skill or CLI command cannot fulfill a specific requirement and they need to discover and invoke the exact native OpenAPI endpoint.386k16k
Just ScrapeQuickly search, crawl, extract structured JSON, or monitor web pages without writing custom scraping code.245k41Lark AppsQuery the current visibility and permission scope of a Lark (Feishu) app without writing HTTP client code.235k16k
Design An InterfaceGenerate multiple radically different interface or API designs in parallel before committing to one.188k198kHow it compares
Pick cost-compact-context when you need compact ReasoningBank context and token savings metrics inside Claude-Flow; use full-context or MCP debug tools when every reasoning step must remain verbatim.
FAQ
What does cost-compact-context return?
cost-compact-context returns compacted ReasoningBank context from getTokenOptimizer().getCompactContext() plus bridge-reported tokensSaved for the supplied cost-analysis query. If agentic-flow is not installed, tokensSaved is 0 and the skill exits cleanly.
Why does cost-compact-context use Bash instead of MCP?
cost-compact-context shells a Node one-liner because ADR-0002 notes no MCP tool wraps getTokenOptimizer yet. Bash allowed-tools execute the integration call directly until an MCP wrapper ships.