Jroute Cli Manager
Director, Policy Gate & Token Ledger add-on for jroute-cli: read-only Fable planner/reviewer, centralized LLM policy gate, and persistent SQLite token tracking.
$1
Works with the AI Agents you already use
About this skill
jroute-cli-manager is the management, governance, and observability extension for jroute-cli.
It adds three production-ready layers using only the Python standard library:
- Director Layer (
jrc_director.py): Afterjrc/jrouteselects the optimal engine, model, and effort, a read-only director model (default:fable,Read,Grep,Globonly) inspects the workspace and.jrc_context.md, writes a concise work order for the executor agent, verifies the executor's report and changed files, and records a single verified architectural note back to.jrc_context.md. - Centralized Policy Gate (
jrc_gate.py,jrc_policy.json,jrc_profiles.py): Single decision point (jrc_gate.decide(source, task)) for all bots, proxies, and background services. Supports per-source model pinning (pin,max_effort,allow_tools), global engine locking (auto | claude | agy), one-shot quota/error fallback (jrc_gate.fallback), JSONL ledger logging (~/.cache/jroute/gate.jsonl), and codebase auditing (jrc_gate.audit()). - Persistent Token Ledger (
jrc_tokens.py): Incrementally indexes Claude Code session transcripts (~/.claude/projects/**/*.jsonl) and CSV cost logs into a permanent SQLite database (~/.cache/jroute/tokens.db), computing 5-hour, daily, 7-day, 30-day, and all-time token & API-equivalent USD summaries with--jsonand dashboard export.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Software
Python 3.10+jroute-cli
Claude CodeorAntigravity CLI