clip
DJPalefaceSD/rostech-mods
Put text on your clipboard from the prompt, cleaned of terminal clutter.
887 mods
DJPalefaceSD/rostech-mods
Put text on your clipboard from the prompt, cleaned of terminal clutter.
DJPalefaceSD/rostech-mods
Files you mark as yours: Claude cannot edit them until you hand them back.
DJPalefaceSD/rostech-mods
Open a link or a file in its own window, straight from the prompt.
DJPalefaceSD/rostech-mods
A chime when Claude finishes a long turn, so you can look away.
DJPalefaceSD/rostech-mods
Hand Claude the picture on your clipboard in one command.
julian-passebecq/claude-mod
Fleet moved into Cockpit (one mod, one window): its To-do and Fleet tabs and /fleet, /dispatch, /todo are now Cockpit's hub tabs. This folder stays only so a machine that still lists it in CLAUDE_CODE_PLUGIN_DIRS loads nothing old: it registers no command, opens no pane and hooks nothing but session.start.
seanGSISG/ad-ldap-plugin
Active Directory administration over LDAPS for Claude Code: an MCP server (FastMCP + ldap3) with 15 tools, admin agents, slash commands, a safety skill, and a guard that refuses any AD write until the identical call has been dry-run first. Headline workflow: mass-assign computer managedBy from description-held owner names via a dry-run plan/review/apply loop.
scaso01/claude-risk-guardrails
Effective challenge: hold answers to evidence under pushback, and check agents' commit claims against git.
scaso01/claude-risk-guardrails
Development standards: look before building, test what changed, pass the repo's checks, keep the rules in view.
scaso01/claude-risk-guardrails
Outcomes analysis: check what a reply claims against what the evidence supports.
scaso01/claude-risk-guardrails
Documentation: leave a trail a reviewer can follow, and keep what can't be rebuilt.
sftinc/claude-code-model-router
Routes each turn and subagent to a model tier and reasoning effort using a classifier behind any server that speaks POST /v1/classify (model-router-api on Cloudflare Workers AI today), falling back to the engine's built-in classifier.
pompeitech/affreschi
Lazzarone: when Claude has been waiting on you for a few minutes (a permission, a question, a long turn just finished), a system notification calls you back
mrayyan911/claude-code-mods
Names a session after a summary of its work when it ends (exit or /clear), and only when work happened since the last rename.
azoof-ahmed/claude-mods
A compact symbol index, markdown section maps and task tags, so Claude reads the index and a few lines instead of whole files.
judybabe/claude-mods
Records every file Write/Edit across sessions and asks before touching a file another session changed in the last 30 minutes.
ramonfabrega/mods
Logs the subscription's rate-limit windows (five_hour, seven_day, and each per-model week such as Fable's: percent used and when each resets) to ~/.lore/limits.jsonl, one line per whole-point move, from every session that has it, and keeps the latest per-model reading in ~/.lore/limits-now.json for a status line to draw — the figures the account enforces, kept, so a week of them gives the...
NikolajMosbaek/claude-tooling
Instant commands that run without a Claude turn: /build-status for the latest xcodebuild, /wt for the worktree list
diegocamara89/claude-mods
Subagente e agente de script (Workflow) criados sem modelo escrito rodam no Sonnet em vez de herdar o Opus; Opus só quando pedido de propósito
hb03/claude-mods
Läuft ein Testbefehl grün durch und liegen danach uncommittete Änderungen im Repo, bekommt Claude still einen Hinweis, den Arbeitsschritt zu committen. Keine Dauerabfrage, kein Git-Hook.
hb03/claude-mods
Prüft vor jedem git push, den Claude in ein öffentliches Repo macht, die neuen Commits auf eigene Muster (Namen, Pfade), fremde Autor-Mails und Geheimnisse. Bei einem Fund fragt sie mit den Fundstellen nach: abbrechen oder trotzdem pushen.
Tvrtk0/claude-code-mods
Holds what your rules forbid: posting to GitHub or pushing without your say-so in your last message, em dashes in posts and commits, an i18n change that skips one of the nine catalogs.
HarzerHeribert/claude-modpack
Optional, and the one mod that needs an outside classifier model: hands feature and test work to delegate's cheaper worker. A fast classifier (TypeSafe's Jev or ScaleDown, with your API key) reads your prompt, and only where it is feature or test work does Claude get the order to implement it through a hand-off. Off until you turn it on and give it a key for one of them.
HarzerHeribert/claude-modpack
Has Claude look around your code in few, lean steps. Every request re-reads the whole conversation, and whatever Claude reads stays in it for every later request; so your prompt, and the task of a subagent Claude starts, carries your setting to batch the searches and reads Claude can already name, to read definitions or line ranges instead of whole files, and not to read again what the session...
No tracking cookies, no third-party scripts. How we handle data