From 6592c31d337853f6eca9148d97a03756c5e287db Mon Sep 17 00:00:00 2001 From: reshuibuduo Date: Fri, 4 Sep 2026 08:01:08 +0800 Subject: [PATCH 1/4] docs: refresh TMCRA Local Memory --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 199761805..247ba84e4 100644 --- a/README.md +++ b/README.md @@ -263,7 +263,7 @@ Third-party plugins built by the community. [PRs welcome](#contributing)! - [Team Skills Platform](https://github.com/Colin4k1024/tsp) - Role-based team delivery framework — Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode. - [Test Gap](./plugins/mturac/test-gap) - Find lines in your diff lacking test coverage (Cobertura, lcov, coverage.json). - [TODO Harvest](./plugins/mturac/todo-harvest) - TODO/FIXME/HACK scan with `git blame` author + age. -- [TMCRA Local Memory](https://github.com/reshuibuduo/tmcra-plugin-codex) - Owner-local memory for Codex that recalls user and project evidence before each answer and carries source-attributed project context across sessions and supported agent tools. +- [TMCRA Local Memory](https://github.com/reshuibuduo/tmcra-plugin-codex) - Automatic long-term memory for Codex with account-scoped global and project recall, role-separated writeback, lifecycle checkpoints, and local Writer and organizer model settings. - [TNT House Risk-Data API](https://github.com/menantonio83-hue/codex-plugin-tnt-risk-api) - Solana token risk scoring for AI trading agents via MCP: safety score, insider wallet cluster detection, mint/freeze authority, honeypot risk, and LP-lock status in one call. - [token-optimizer](https://github.com/ooples/token-optimizer-mcp) - Cut token usage 60-90% with caching, compression, and smart file tools — diff-only re-reads, paths-only search, out-of-context stashing, and a per-tool savings report for Codex and Claude Code. - [Tool Advisor](https://github.com/dragon1086/claude-skills) - Read-only meta-skill that scans your MCP servers, skills, plugins, and CLI tools, then suggests up to three ranked approaches (Methodical / Fast / Deep) with a copy-paste Quick Action table. From 9e28c632e49ed9b211a0b76165636ff31873fb29 Mon Sep 17 00:00:00 2001 From: reshuibuduo Date: Fri, 4 Sep 2026 08:24:53 +0800 Subject: [PATCH 2/4] chore: restore README alphabetical order --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 247ba84e4..760005058 100644 --- a/README.md +++ b/README.md @@ -196,8 +196,8 @@ Third-party plugins built by the community. [PRs welcome](#contributing)! - [Context Guard](https://github.com/GreenLv/codex-context-guard) - Preserves authoritative requirements and verification evidence across long-running Codex tasks and context compaction. - [debt-ops](https://github.com/bcanfield/agentic-tech-debt) - Catches AI-introduced tech debt at write-time: hooks log every deferral to a registry in your repo and a review skill ranks paydown by file churn. - [DeepSeek Mini-Router](https://github.com/hccccc01333/codex-deepseek-mini-router) - Task-aware spec/react/flash working-contract plugin that fixes DeepSeek weak default reasoning inside Codex, with a measured BigCodeBench harness included. -- [Deps Doctor](./plugins/mturac/deps-doctor) - Multi-ecosystem dependency audit (npm, pip, cargo, go) in one report. - [Delx Recovery](https://github.com/davidmosiah/delx-plugins) - Free recovery and continuity plugin for AI agents: resume prior sessions, capture state, process failures into a recovery plan, and remember across sessions through a hosted MCP server (works in Codex, Claude Code, Cursor, and VS Code). +- [Deps Doctor](./plugins/mturac/deps-doctor) - Multi-ecosystem dependency audit (npm, pip, cargo, go) in one report. - [Designer Skill](https://github.com/Pythoughts-labs/designer-skill) - Plug-and-play MCP that gives your agent UI superpowers. One install: design skill + MCP server, zero config. - [Dev Skills](https://github.com/Jason-chen-coder/dev-skills) - Team workflow skills for specs, plans, TDD, debugging, verification, review, branch finishing, and design context. - [Development Skills](https://github.com/reidemeister94/development-skills) - Three-tier triage (PASS_THROUGH / LIGHT / FULL 4-phase) development workflow for Codex and Claude Code with language auto-detection (Python, Java, TypeScript, Swift, frontend) and a staff-reviewer subagent for fresh-eyes review on every change. @@ -262,9 +262,9 @@ Third-party plugins built by the community. [PRs welcome](#contributing)! - [Tartiner Labs](https://github.com/tartinerlabs/skills) - Agent skills for git workflows, GitHub automation, security audits, code refactoring, and project tooling. - [Team Skills Platform](https://github.com/Colin4k1024/tsp) - Role-based team delivery framework — Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode. - [Test Gap](./plugins/mturac/test-gap) - Find lines in your diff lacking test coverage (Cobertura, lcov, coverage.json). -- [TODO Harvest](./plugins/mturac/todo-harvest) - TODO/FIXME/HACK scan with `git blame` author + age. - [TMCRA Local Memory](https://github.com/reshuibuduo/tmcra-plugin-codex) - Automatic long-term memory for Codex with account-scoped global and project recall, role-separated writeback, lifecycle checkpoints, and local Writer and organizer model settings. - [TNT House Risk-Data API](https://github.com/menantonio83-hue/codex-plugin-tnt-risk-api) - Solana token risk scoring for AI trading agents via MCP: safety score, insider wallet cluster detection, mint/freeze authority, honeypot risk, and LP-lock status in one call. +- [TODO Harvest](./plugins/mturac/todo-harvest) - TODO/FIXME/HACK scan with `git blame` author + age. - [token-optimizer](https://github.com/ooples/token-optimizer-mcp) - Cut token usage 60-90% with caching, compression, and smart file tools — diff-only re-reads, paths-only search, out-of-context stashing, and a per-tool savings report for Codex and Claude Code. - [Tool Advisor](https://github.com/dragon1086/claude-skills) - Read-only meta-skill that scans your MCP servers, skills, plugins, and CLI tools, then suggests up to three ranked approaches (Methodical / Fast / Deep) with a copy-paste Quick Action table. - [Tree Ring Memory](https://github.com/TerminallyLazy/tree-ring-memory-codex-plugin) - Local-first memory lifecycle guidance for Codex agents with recall, evidence-backed lessons, privacy-safe memory capture, audit, consolidation, and explicit forgetting. @@ -454,8 +454,8 @@ The score is best used as a quick trust signal and triage summary (not the only ## Related Projects - [awesome-ai-plugins](https://github.com/hashgraph-online/awesome-ai-plugins) - Umbrella list covering Codex, Claude Code, Gemini CLI, and MCP servers. -- [Tura](https://github.com/Tura-AI/tura) - A local, open-source coding agent for developers who are tired of vague skill claims, token-saving extensions with no evidence, and agents that change a repository before understanding it. - [HOL Plugin Registry](https://hol.org/registry/plugins) - Browse plugins with scanner-backed security analysis and trust scores. +- [Tura](https://github.com/Tura-AI/tura) - A local, open-source coding agent for developers who are tired of vague skill claims, token-saving extensions with no evidence, and agents that change a repository before understanding it. ## Claim Your Plugin From 40f38b106bf21814b25e16a40f53bcd9b31f5d8e Mon Sep 17 00:00:00 2001 From: reshuibuduo Date: Fri, 4 Sep 2026 08:27:23 +0800 Subject: [PATCH 3/4] Revert "chore: restore README alphabetical order" This reverts commit 9e28c632e49ed9b211a0b76165636ff31873fb29. --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 760005058..247ba84e4 100644 --- a/README.md +++ b/README.md @@ -196,8 +196,8 @@ Third-party plugins built by the community. [PRs welcome](#contributing)! - [Context Guard](https://github.com/GreenLv/codex-context-guard) - Preserves authoritative requirements and verification evidence across long-running Codex tasks and context compaction. - [debt-ops](https://github.com/bcanfield/agentic-tech-debt) - Catches AI-introduced tech debt at write-time: hooks log every deferral to a registry in your repo and a review skill ranks paydown by file churn. - [DeepSeek Mini-Router](https://github.com/hccccc01333/codex-deepseek-mini-router) - Task-aware spec/react/flash working-contract plugin that fixes DeepSeek weak default reasoning inside Codex, with a measured BigCodeBench harness included. -- [Delx Recovery](https://github.com/davidmosiah/delx-plugins) - Free recovery and continuity plugin for AI agents: resume prior sessions, capture state, process failures into a recovery plan, and remember across sessions through a hosted MCP server (works in Codex, Claude Code, Cursor, and VS Code). - [Deps Doctor](./plugins/mturac/deps-doctor) - Multi-ecosystem dependency audit (npm, pip, cargo, go) in one report. +- [Delx Recovery](https://github.com/davidmosiah/delx-plugins) - Free recovery and continuity plugin for AI agents: resume prior sessions, capture state, process failures into a recovery plan, and remember across sessions through a hosted MCP server (works in Codex, Claude Code, Cursor, and VS Code). - [Designer Skill](https://github.com/Pythoughts-labs/designer-skill) - Plug-and-play MCP that gives your agent UI superpowers. One install: design skill + MCP server, zero config. - [Dev Skills](https://github.com/Jason-chen-coder/dev-skills) - Team workflow skills for specs, plans, TDD, debugging, verification, review, branch finishing, and design context. - [Development Skills](https://github.com/reidemeister94/development-skills) - Three-tier triage (PASS_THROUGH / LIGHT / FULL 4-phase) development workflow for Codex and Claude Code with language auto-detection (Python, Java, TypeScript, Swift, frontend) and a staff-reviewer subagent for fresh-eyes review on every change. @@ -262,9 +262,9 @@ Third-party plugins built by the community. [PRs welcome](#contributing)! - [Tartiner Labs](https://github.com/tartinerlabs/skills) - Agent skills for git workflows, GitHub automation, security audits, code refactoring, and project tooling. - [Team Skills Platform](https://github.com/Colin4k1024/tsp) - Role-based team delivery framework — Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode. - [Test Gap](./plugins/mturac/test-gap) - Find lines in your diff lacking test coverage (Cobertura, lcov, coverage.json). +- [TODO Harvest](./plugins/mturac/todo-harvest) - TODO/FIXME/HACK scan with `git blame` author + age. - [TMCRA Local Memory](https://github.com/reshuibuduo/tmcra-plugin-codex) - Automatic long-term memory for Codex with account-scoped global and project recall, role-separated writeback, lifecycle checkpoints, and local Writer and organizer model settings. - [TNT House Risk-Data API](https://github.com/menantonio83-hue/codex-plugin-tnt-risk-api) - Solana token risk scoring for AI trading agents via MCP: safety score, insider wallet cluster detection, mint/freeze authority, honeypot risk, and LP-lock status in one call. -- [TODO Harvest](./plugins/mturac/todo-harvest) - TODO/FIXME/HACK scan with `git blame` author + age. - [token-optimizer](https://github.com/ooples/token-optimizer-mcp) - Cut token usage 60-90% with caching, compression, and smart file tools — diff-only re-reads, paths-only search, out-of-context stashing, and a per-tool savings report for Codex and Claude Code. - [Tool Advisor](https://github.com/dragon1086/claude-skills) - Read-only meta-skill that scans your MCP servers, skills, plugins, and CLI tools, then suggests up to three ranked approaches (Methodical / Fast / Deep) with a copy-paste Quick Action table. - [Tree Ring Memory](https://github.com/TerminallyLazy/tree-ring-memory-codex-plugin) - Local-first memory lifecycle guidance for Codex agents with recall, evidence-backed lessons, privacy-safe memory capture, audit, consolidation, and explicit forgetting. @@ -454,8 +454,8 @@ The score is best used as a quick trust signal and triage summary (not the only ## Related Projects - [awesome-ai-plugins](https://github.com/hashgraph-online/awesome-ai-plugins) - Umbrella list covering Codex, Claude Code, Gemini CLI, and MCP servers. -- [HOL Plugin Registry](https://hol.org/registry/plugins) - Browse plugins with scanner-backed security analysis and trust scores. - [Tura](https://github.com/Tura-AI/tura) - A local, open-source coding agent for developers who are tired of vague skill claims, token-saving extensions with no evidence, and agents that change a repository before understanding it. +- [HOL Plugin Registry](https://hol.org/registry/plugins) - Browse plugins with scanner-backed security analysis and trust scores. ## Claim Your Plugin From 0d4b18724c25732501ca26c0655ad01700f9b9cd Mon Sep 17 00:00:00 2001 From: reshuibuduo Date: Sun, 6 Sep 2026 03:47:25 +0800 Subject: [PATCH 4/4] docs: refresh TMCRA for unified 1.0.0-rc.1 capabilities --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 247ba84e4..6ae02affa 100644 --- a/README.md +++ b/README.md @@ -263,7 +263,7 @@ Third-party plugins built by the community. [PRs welcome](#contributing)! - [Team Skills Platform](https://github.com/Colin4k1024/tsp) - Role-based team delivery framework — Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode. - [Test Gap](./plugins/mturac/test-gap) - Find lines in your diff lacking test coverage (Cobertura, lcov, coverage.json). - [TODO Harvest](./plugins/mturac/todo-harvest) - TODO/FIXME/HACK scan with `git blame` author + age. -- [TMCRA Local Memory](https://github.com/reshuibuduo/tmcra-plugin-codex) - Automatic long-term memory for Codex with account-scoped global and project recall, role-separated writeback, lifecycle checkpoints, and local Writer and organizer model settings. +- [TMCRA Local Memory](https://github.com/reshuibuduo/tmcra-plugin-codex) - Automatic project memory with a visual knowledge workspace, chat-confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview. - [TNT House Risk-Data API](https://github.com/menantonio83-hue/codex-plugin-tnt-risk-api) - Solana token risk scoring for AI trading agents via MCP: safety score, insider wallet cluster detection, mint/freeze authority, honeypot risk, and LP-lock status in one call. - [token-optimizer](https://github.com/ooples/token-optimizer-mcp) - Cut token usage 60-90% with caching, compression, and smart file tools — diff-only re-reads, paths-only search, out-of-context stashing, and a per-tool savings report for Codex and Claude Code. - [Tool Advisor](https://github.com/dragon1086/claude-skills) - Read-only meta-skill that scans your MCP servers, skills, plugins, and CLI tools, then suggests up to three ranked approaches (Methodical / Fast / Deep) with a copy-paste Quick Action table.