ワンクリックで
savings
Report rtk and jcodemunch token savings for the current session.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Report rtk and jcodemunch token savings for the current session.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Invoke BEFORE any design or feature work. Wraps superpowers:brainstorming with scout agent context harvesting, stack-first design considerations, and constitutional rule awareness. Asks questions one at a time to refine the design.
Invoke AFTER brain+ design is approved. Wraps superpowers:writing-plans with constitutional rules, testing strategy per task, and mock policy. Creates bite-sized implementation plans.
Invoke AFTER verify+ passes. Wraps superpowers:requesting-code-review with constitutional compliance checklist, stale test validation, and reviewer agent invocation. Two-stage review: spec compliance + code quality.
Invoke AFTER plan+ is approved. Wraps superpowers:test-driven-development with full-loop assertions, real-dependency enforcement for stack tests, zero-defect, stale test detection, and scoped test runs. Implements plan tasks with RED-GREEN-REFACTOR discipline.
Run after `rig init` to verify all hooks, skills, and agents are installed and working correctly in the live session.
Invoke AFTER tdd+ implementation is complete. Wraps superpowers:verification-before-completion with evidence standards, spec drift check, and full-suite test run. This is the ONLY phase where full test suite runs are appropriate.
| name | savings |
| description | Report rtk and jcodemunch token savings for the current session. |
| argument-hint | |
| user-invocable | true |
Report token savings from rtk and jcodemunch usage during this session.
rtk gain --format json to get current savings data. If rtk is not
available, skip rtk reporting.ls /tmp/rig-session-*.json. Read the most
recent one (by modification time). It contains metricsBaseline,
metricCounters (rtkCalls, jmCalls, efficientCalls), and environment
(rtkAvailable, jcodemunchAvailable).current total_saved - baseline totalSaved.mcp__jcodemunch__get_session_stats and read
session_tokens_saved, session_calls, total_tokens_saved, and
tool_breakdown directly. These are reliable per-session counters
maintained by the MCP server process. If jcodemunch MCP is not available,
skip jcodemunch reporting.With session data (baseline + delta available):
[rig] Session Savings
rtk: X.XM saved (N calls, +XK this session)
jcodemunch: XK saved (N queries, 150M total all-time)
Without session data (no cache file found):
[rig] Session Savings (all-time)
rtk: X.XM saved (N commands, XX.X% avg savings)
If rtk is not installed:
[rig] Session Savings
rtk: not installed
X.XM, >=1K as XK, else raw number.session_tokens_saved and session_calls come directly from
get_session_stats. total_tokens_saved is the all-time cumulative.