Consultation and prompt engine for Claude Mods. The module is the core; [probe. ] tables in probes.toml are the consultants and [prompt. ] tables author a system-prompt section, a tool description or a command description. The only carrier is the mod: a CLAUDE_*_CARRIER handle set to mod or left empty/unset arms the probe here; any other value loudly refuses the calls this probe acts on (the...
catalyst-swe-request
TransmuteLabs/Catalyst
Request-text policy for devin/swe-2: registers one rule in the host's $.requestText noun.
jev-gate
MongLong0214/jev-gate
Jev Gate in one plugin: the orchestration gate, the extractive compactor, the Vitest log folder, the Jev effort and model router and the jev_evidence tool. Every part is on by default; each has its own on/off option.
jev-gate-compact
MongLong0214/jev-gate
Answers auto compactions with an extractive digest and the recent tail, so compacting sends no summarizer request and has no wait; on by default.
jev-gate-output
MongLong0214/jev-gate
Folds runs of identical consecutive lines in a passing Vitest log the host saved to a file, so the model reads the whole run with exact counts instead of a 2 KB preview; on by default.
superlcm
yu381792/superlcm
One local conversation archive for Claude Code, Codex, Hermes, Pi and dsh harness. Keep full original records, browse layered summaries, recall exact sources and continue tasks across tools. SuperLcm supports opt-in compaction takeover in Claude Code and dsh harness; DSH model and retention settings are managed in the DSH SuperLcm plugin settings. Open /superlcm:console to connect the other...
websearch-perplexity
riethmayer/dotfiles
Routes the WebSearch tool to Perplexity (pplx CLI) via a function hook; falls back to native search on failure
noctis
synex1437/noctis
Runs long Claude Code jobs overnight within your usage limits: pauses just before the 5-hour or weekly limit, resumes the same session after the reset (or relaunches it days later) and works through a list of jobs you hand it with /noctis:start . Also runs in Codex CLI, Antigravity CLI, Droid and Copilot CLI.
wt-deep-search
home-dev-lab/workflow-toolbox
EXPERIMENTAL. Answers a WebSearch from the local Claude Code doc mirror, context7, Brave or Exa, and adds a detached deep-research rung behind a handle.
wt-rules-on-demand
home-dev-lab/workflow-toolbox
EXPERIMENTAL. Deliver frontmatter-triggered rules at matching prompts and tool calls.
agent-models
alex2481kobe/claude-mods
Each Claude subagent's model and effort in the native agent list, beside its task
agent-bridge
rennerdo30/agent-bridge
Talk to OpenAI Codex from Claude Code: live peer messaging over a local pipe, plus headless delegation (ask_codex).
redact
karanb192/claude-code-redact
Redacts secrets and PII from every row Claude Code stores, before the model reads it and before the transcript keeps it. Reach L0: no network, no processes, no files.
idle-compactor
ymnao/dotfiles
Compacts an idle Claude Code session shortly before its 1-hour prompt cache expires, so coming back later re-sends a short summary instead of the whole conversation uncached.
quarry
jackboykin/quarry
Adds Exa's results to WebSearch, and saves each WebFetch page to disk with the lines that answer the prompt
persistent-monitor
ruihe774/cc-persistent-monitor
Monitor tool with persistent (no deadline) watches
classify-hint
corrupt952/dotfiles
Classifies the user's prompt with Haiku against a few yes/no questions in one call and attaches a rough, non-binding hint for the main agent
explore-model
rlorenzo/ai-coding-setup
Pins the model that background recon subagents run on. An agent.spawn hook sets the Explore subagent's model to haiku, so a session driven by an expensive model stops billing its codebase searches at that tier, without shadowing the built-in agent definition and without the CLAUDE.md load a replacement definition would cost.
review-gate
rlorenzo/ai-coding-setup
The review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls -- almost all of them -- cost no subprocess at all, and a blocked commit can be put to you as a question instead of refused outright. The decision itself is still bin/review-gate, run only for a command that mentions a commit, so both routes read the same receipts and cannot disagree.
Blinks the iTerm2 tab orange when a turn lands, for up to three minutes or until you type again, so a finished session is obvious from any other tab.
merge-gate
yash-gadodia/claude-mods
Denies a Bash merge (gh pr merge, git merge on main, push onto main) unless the latest human message says the word merge; ship, push and deploy do not count.