codex

Session Improvement Loop

Research uncertain decisions and local inference candidates, and independently validate reusable workflow improvements.

0 on GitHubby Fakoliv0.2.1MITupdated todayProductivity

Plugin session-improvement-loop in fakoli/agent-plugins. Commands read from the repo's manifest — today.

What it installs

Skills (4)

  • local-inference-research

    Research local inference models, runtimes, quantization, and agent harnesses against the user's hardware and workloads. Reuse a project's model decision tracker for repeated comparisons and refresh changed evidence. Produces cited research, not deployment or model qualification.

  • research-synthesis

    Make an evidence-backed decision from bounded independent research. Use when a material technical, product, operational, or implementation choice remains unresolved and independent answers could change the next action; do not use for routine lookups or an established single-setting remedy.

  • review-session-improvements

    Review recent Codex or Claude session logs for recurring token waste, accuracy failures, slow manual work, and user-experience friction; then propose, create, or update only evidence-backed skills and plugins. Use for daily session reviews, cross-session improvement audits, proactive skill discovery

  • skill-improvement

    Improve an agent skill from observed evidence using a frozen baseline, matched controls, independent judgment, and holdout cases. Use at a campaign boundary or after a material process failure; do not use for speculative rewrites or account-wide memory changes.

View source on GitHub

More from fakoli/agent-plugins

All 7 plugins →

Diagnose GPU ownership and credential-loading boundaries without exposing secrets or making unreviewed host changes.

2 skills

0

Coordinate bounded tasks, saved Pi conversations and model capability discovery inside NVIDIA OpenShell.

1 skill

0

Prepare evidence-backed retrospective design reviews and article inputs after a feature build.

1 skill

0

Local repository diagrams and incremental search for large codebases.

1 skill

0

Turn an external gist, README, issue, or runbook into a pinned comparison and safe local test plan.

1 skill

0

Coordinate changes across related repositories and worktrees while preserving dirty state and ownership boundaries.

1 skill

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

Maintain Session Improvement Loop?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins