Skip to content

Add the token efficiency plan for issue 766 - #785

Merged
ptr727 merged 2 commits into
developfrom
feature/issue-766-token-efficiency-plan
Aug 17, 2026
Merged

Add the token efficiency plan for issue 766#785
ptr727 merged 2 commits into
developfrom
feature/issue-766-token-efficiency-plan

Conversation

@ptr727

@ptr727 ptr727 commented Aug 17, 2026

Copy link
Copy Markdown
Owner

Summary

Adds docs/token-efficiency-plan.md, the hub-only rollout plan for #766. The delivery is the doc, the work is the analysis, architecture, and design.

  • Objectives: lower recurring context, improve accuracy, progressive disclosure as the default shape, empirical decisions for locked content, preserve invariants, agent-executable delivery.
  • Gap analysis: 10 measured gaps at 5b8e008, the largest being the Copilot Review Runbook at 47.6 KB of the 53.2 KB always-loaded Copilot file, and 12 of 18 skills without references/.
  • Rollout plan: one checkbox = one worktree = one PR, benchmark veto for behavior-affecting edits, per-fidelity-class propagation, Findings Register for defects.
  • Phased delivery: Phase 0 records Expand references/ in large skill files for progressive disclosure (#766 Phase 2) #773, Phase 1 builds the measuring sticks (inventory script + benchmark), Phases 2-3 execute the proven reductions, Phase 4 measures downstream per-provider context, Phases 5-7 are gated on that evidence.

Closes #766 (the plan is the delivery, the phases self-track progress).

Objectives, gap analysis, rollout protocol, and seven delivery phases
for reducing recurring instruction cost without weakening behavior.
Every phase is checkbox-tracked so agents execute and record results
in the doc, with a benchmark and inventory script as the veto gates.
Copilot AI lite review requested due to automatic review settings August 17, 2026 02:52

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new hub-only rollout plan document that breaks down issue #766 into measurable gaps, a phased execution protocol, and a metrics/findings log to track progress on token-efficiency work across the fleet.

Changes:

  • Add docs/token-efficiency-plan.md defining objectives, cost model, gap analysis, rollout protocol, and phased delivery for #766.
  • Include baseline metrics and an ongoing re-measure log plus a findings register to track discovered defects separately from fixes.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment thread docs/token-efficiency-plan.md Outdated
Comment thread docs/token-efficiency-plan.md Outdated
Copilot AI review requested due to automatic review settings August 17, 2026 02:59

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

@ptr727
ptr727 merged commit 22ecc53 into develop Aug 17, 2026
8 checks passed
@ptr727
ptr727 deleted the feature/issue-766-token-efficiency-plan branch August 17, 2026 03:08
ptr727 added a commit that referenced this pull request Aug 17, 2026
Promote `develop` to `main`, carrying:

- #785 Add the token efficiency plan for issue 766

This promotion contains the documentation plan committed on `develop`
since the previous promotion.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants