Everyday defaults for Claude Code: repo grounding, the always-on engineering rules, core skills, and the specialist agents.
✳︎ dev-core
└─ Make every conversation easier
Explore repeatable development workflows and CI integrations.
261 projectsEveryday defaults for Claude Code: repo grounding, the always-on engineering rules, core skills, and the specialist agents.
Everythings for Claude Code: MCP tools for a notes, lists and projects collaboration workspace, including project search, reading and editing plus remote questions and answers.
The guard-heavy-commands hook keeps measuring a heavy process it stopped because CPU is under pressure, then notifies the session when the system has room again.
BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗A pomodoro timer on the prompt's hint line in Claude Code, whose break lands while Claude works; includes commands, buttons, history, reports and Open Pomodoro integration.
A Claude Code plugin built with function hooks that shows each turn's typed prompt alongside Claude Code's last answer for that turn in a side pane via the /conversation command.
# session-board A Claude Code mod for people who run many sessions at once: a task brief at the start, an Acceptance screen and an interactive HTML report at the end, and a task folder that survives compaction. The board speaks Russian; the ledger Claude reads is in plain English. Install and safety: see the [main README](../../README.md).
A Claude Code mod that keeps the number of running Claude Code sessions under a limit, warns you on prompt submit when at or over the limit, and shows which sessions are waiting on you or sitting idle.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗Blocks dependency changes with the wrong package manager or outside a repo, and shows repo, package manager and branch in the status line.
A Claude Code plugin in the agent-tack suite that provides a live panel showing the agent's tool calls, skills, subagents, and permission decisions.
A Claude Code plugin pane for answering the question rounds of the grilling / grill-me skill, turning selected answers into the next prompt.
A Claude Code plugin that runs a disciplined, self-improving development loop: every phase's failures are logged, turned into evals, and rewritten into the skills and agents that caused them.
ByxIn's brain inside Claude Code: grounded answers checked against what was shown, an honest record, and one shared brain for every session in a project, local or remote.
Top 3 by votes, then GitHub stars
No. Votes and stars measure popularity. Review the source and permission scan before installing.