matebenyovszky/agentplaybooks

Equip once. Run anywhere. Portable AI agents and toolkits—no vendor lock-in.

10Stars on the repository
21Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

commit-message

01

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Write a conventional, imperative git commit message from the staged diff. Use when committing, amending, or rewriting a commit message.

not rated 10 +1 today A 29 tokens original MIT

pr-hygiene

02

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Check a pull request is small, described, tested, and free of secrets before opening or reviewing it. Use when drafting a PR, reviewing a diff, or verifying a change is ready to share.

not rated 10 +1 today A 45 tokens original MIT

session-handoff

03

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Write a short end-of-session handoff covering what changed, what is left, and how to resume. Use when wrapping up a Cursor or Hermes session.

not rated 10 +1 today A 35 tokens original MIT

task-breakdown

04

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Split a request into a short ordered checklist of local edits and checks. Use when a task is too large for one step or needs a plan before coding.

not rated 10 +1 today A 35 tokens original MIT

review-notes

05

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Write a focused code review covering correctness, tests, and follow-ups. Use when reviewing a diff or summarizing review comments.

not rated 10 +1 today A 29 tokens original MIT

changelog-notes

06

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Draft user-facing changelog bullets from a diff or merged PR. Use when writing release notes, CHANGELOG entries, or a PR summary for humans.

not rated 10 +1 today A 35 tokens original MIT

issue-triage

07

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Reproduce a bug report, judge severity, and propose the next step. Use when an issue, ticket, or error report needs a first response.

not rated 10 +1 today A 35 tokens original MIT

test-plan

08

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Turn a code change into a short manual and automated test plan. Use when a feature, fix, or refactor needs verification steps.

not rated 10 +1 today A 30 tokens original MIT

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Connect AgentPlaybooks skills, MCP servers, and federated OpenAPI tools to Hermes. Guide playbook sync, authentication, secret setup, and recovery.

not rated 10 +1 changed 6d ago A 36 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: