O
onurmicoogullari/agent-tools
Reusable skills, specialist agent profiles, and configuration for Codex, Claude Code, and OpenCode
★ 1·updated 2026-11-16
View on GitHub ↗Link checked 2026-11-17 · HTTP 200 · opens the vendor's own site
- Star count
- 1 ★ · onurmicoogullari/agent-tools · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-17 · last seen 2026-11-20 · seen 4× · listed by 1 sources
- Score
- score 103 · 1 ★ · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Open Source. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
onurmicoogullari/agent-tools;first catalogued 2026-11-17;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# agent-tools
Excerpted from the repository README (abridged)
A personal collection of reusable skills, specialist agent profiles, and configuration for Codex, Claude Code, and OpenCode. It covers everyday development workflows, backend and platform engineering, interface design, and documentation.
Codex is the source of truth. Claude Code and OpenCode receive adaptations that use each tool's native skill, command, and agent formats. A few Claude-only additions are listed under skills and agent profiles.
## Repository structure
text
├── codex/ # Canonical skills and Codex configuration
│ ├── AGENTS.md # Personal working instructions
│ ├── agents/ # Five specialist profiles in TOML
│ ├── skills/ # Personal skills and their supporting files
│ │ └── .system/ # Archived Codex system skills; skip installation
│ └── scripts/ # Launchers that select a local Kubernetes configuration
├── claude/ # Claude Code adaptations
│ ├── CLAUDE.md # Personal working instructions
│ ├── agents/ # Eight native agent profiles
│ ├── skills/ # Skills with Claude-specific metadata
│ └── settings.json # Optional settings and plugin preferences
├── opencode/ # OpenCode adaptations
│ ├── AGENTS.md # Personal working instructions
│ ├── agents/ # Eight native agent profiles
│ ├── skills/ # Skills loaded through OpenCode's skill tool
│ ├── commands/ # Explicit /plan workflow
│ ├── plugin/ # Local Kubernetes configuration plugin
│ ├── opencode.jsonc # Skill permissions and plugin configuration
│ └── tui.jsonc # Terminal interface preferences
├── docs/skill-sync.md # Adaptation decisions and maintenance guidance
├── LICENSE # MIT license for original work
└── THIRD_PARTY.md # Upstream licenses and attribution
Each skill is a directory containing a SKILL.md entry point. Some include references, examples, helper scripts, evaluation fixtures, or assets. Copy the whole directory, including any license and notice files.
## What's included
Development workflows: code review, guided pull request review, simplification, commits, pull requests, CI troubleshooting, and explanations of unfamiliar code.
Engineering: backend services, Go, Rust, Kubernetes/OpenShift, infrastructure as code, developer platforms, security, observability, and reliability.
Interface design: frontend design plus focused workflows for accessibility audits, layout, typography, animation, responsiveness, performance, and polish.
Planning and documentation: implementation plans, design interviews, writing for docs, emails, and messages, diagrams, Azure DevOps work items, and Notion workflows.
Teaching: platform engineering explained from zero for a trainee, with printable primers, ticket breakdowns, coaching, and quizzes (Claude Code only).
Some skills reflect personal team conventions. In particular, review the project and team defaults in azure-devops-author, and the learner profile and app-platform repository references in platform-tutor, before adopting them elsewhere. Integration skills need their corresponding CLI, service connection, or local dependencies; copying a skill does not configure those services.
## Skills and agent profiles
Skills provide reusable instructions for a task in the current conversation. Agent profiles define a specialist role for delegated work. Interactive planning and questions stay in the main conversation; advisory agents provide focused research, architecture, debugging, or review.
Codex is the source of truth. Claude Code and OpenCode receive adaptations that use each tool's native skill, command, and agent formats. A few Claude-only additions are listed under skills and agent profiles.
## Repository structure
text
├── codex/ # Canonical skills and Codex configuration
│ ├── AGENTS.md # Personal working instructions
│ ├── agents/ # Five specialist profiles in TOML
│ ├── skills/ # Personal skills and their supporting files
│ │ └── .system/ # Archived Codex system skills; skip installation
│ └── scripts/ # Launchers that select a local Kubernetes configuration
├── claude/ # Claude Code adaptations
│ ├── CLAUDE.md # Personal working instructions
│ ├── agents/ # Eight native agent profiles
│ ├── skills/ # Skills with Claude-specific metadata
│ └── settings.json # Optional settings and plugin preferences
├── opencode/ # OpenCode adaptations
│ ├── AGENTS.md # Personal working instructions
│ ├── agents/ # Eight native agent profiles
│ ├── skills/ # Skills loaded through OpenCode's skill tool
│ ├── commands/ # Explicit /plan workflow
│ ├── plugin/ # Local Kubernetes configuration plugin
│ ├── opencode.jsonc # Skill permissions and plugin configuration
│ └── tui.jsonc # Terminal interface preferences
├── docs/skill-sync.md # Adaptation decisions and maintenance guidance
├── LICENSE # MIT license for original work
└── THIRD_PARTY.md # Upstream licenses and attribution
Each skill is a directory containing a SKILL.md entry point. Some include references, examples, helper scripts, evaluation fixtures, or assets. Copy the whole directory, including any license and notice files.
## What's included
Development workflows: code review, guided pull request review, simplification, commits, pull requests, CI troubleshooting, and explanations of unfamiliar code.
Engineering: backend services, Go, Rust, Kubernetes/OpenShift, infrastructure as code, developer platforms, security, observability, and reliability.
Interface design: frontend design plus focused workflows for accessibility audits, layout, typography, animation, responsiveness, performance, and polish.
Planning and documentation: implementation plans, design interviews, writing for docs, emails, and messages, diagrams, Azure DevOps work items, and Notion workflows.
Teaching: platform engineering explained from zero for a trainee, with printable primers, ticket breakdowns, coaching, and quizzes (Claude Code only).
Some skills reflect personal team conventions. In particular, review the project and team defaults in azure-devops-author, and the learner profile and app-platform repository references in platform-tutor, before adopting them elsewhere. Integration skills need their corresponding CLI, service connection, or local dependencies; copying a skill does not configure those services.
## Skills and agent profiles
Skills provide reusable instructions for a task in the current conversation. Agent profiles define a specialist role for delegated work. Interactive planning and questions stay in the main conversation; advisory agents provide focused research, architecture, debugging, or review.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/onurmicoogullari-agent-tools/)
- Source
- github · https://github.com/onurmicoogullari/agent-tools
- Browse by field
- Open source
- Traction
- 1 ★
- added
- today
More entries
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.