From e882eea2ee243b42c8ce17e6f535e1aa69cdfcea Mon Sep 17 00:00:00 2001 From: Julian Lechner Date: Wed, 16 Sep 2026 19:18:27 +0200 Subject: [PATCH] docs(plans): mark token efficiency plan as historical --- docs/superpowers/plans/2026-09-16-token-efficiency.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/superpowers/plans/2026-09-16-token-efficiency.md b/docs/superpowers/plans/2026-09-16-token-efficiency.md index a16dcc5..14c8bc6 100644 --- a/docs/superpowers/plans/2026-09-16-token-efficiency.md +++ b/docs/superpowers/plans/2026-09-16-token-efficiency.md @@ -1,6 +1,6 @@ # Token-Efficiency Improvements Implementation Plan -> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. +> Historical implementation plan, retained for context. It is not a current runbook or authorization to execute its commands. Checkboxes do not represent current completion status. Later changes supersede its validation requirements and examples; use [AI-Instructions.md](../../../AI-Instructions.md) and the [README](../../../README.md) for current guidance. Commit steps below require explicit user authorization. **Goal:** Cut low-value tokens agents pay for in both Claude Code and Codex — chatty script output, always-loaded rule content that's rarely needed in full, duplicated instructions, and low-value delegation — without weakening correctness, security, or verification quality.