Skills I use to execute long-running coding agents without breaking my back.
Plugin Claude Code
Bundles 1 skill · 93 tokens together
Self-QA a repo's running app end-to-end — discover run/auth/features, build a feature×modality test matrix, execute it live, and produce a witnessed pass/fail report.
Plugin Claude Code
Bundles 1 skill · 36 tokens together
Carry large projects through verifiable tasks, parallel work, and durable progress.
Plugin Claude Code
Bundles 1 skill · 104 tokens together
Turn whole-codebase slop into evidence-backed cleanup with the official Desloppify engine.
Plugin Claude Code
Bundles 1 skill · 88 tokens together
Route AI coding-assistant questions and approvals to a phone call through Vapi. Works with Claude Code, Codex, and pi.
Plugin Claude Code
Bundles 1 skill, 1 plugin · 115 tokens together
Multi-model orchestration or explicit solo execution: route work across capable models, or run one exact proxy model with delegation disabled.
Plugin Claude Code
Bundles 1 skill · 140 tokens together
Indexed search over Claude Code + Codex session history — find, continue, repeat, or skill-ify prior work.
Plugin Claude Code
Bundles 1 skill · 122 tokens together
Evidence-backed end-to-end comprehension of one exact coding-agent session.
Plugin Claude Code
Bundles 1 skill · 64 tokens together
Keep Slack threads attached to their Claude Code, Codex, Zellij, or headless agents through Hermes.
Plugin Claude Code
Bundles 1 skill · 166 tokens together
Write a grounded recap of a task as if it were already done, then use it to check whether a long-running agent is still on the imagined path.
Plugin Claude Code
Bundles 1 skill · 61 tokens together
Find what a diff breaks beyond the diff and prove the one safety fact by running real code instead of writing it up.
Plugin Claude Code
Bundles 1 skill · 118 tokens together
Drive every reviewer thread on a GitHub PR (Greptile, Devin, humans) to zero unresolved in bounded iterations, with a fixed-format final report.
Plugin Claude Code
Bundles 1 skill · 33 tokens together
Test-driven development at pre-agreed seams: red before green, one vertical slice per cycle, regression-first bug fixes.
Plugin Claude Code
Bundles 1 skill · 48 tokens together
Cut AI tells from text written or edited for a human reader before committing, posting, or sending it.
Plugin Claude Code
Bundles 1 skill · 76 tokens together
Verify that the intended release candidate is live in its target environment and that the changed path works there, with live evidence.
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: