88plug

88plug/searxng-mcp

Plugin Claude Code

Fast, token-efficient MCP for SearXNG metasearch. Privacy-respecting search across 70+ engines with stdio + streamable-http transports, Docker, and optional ren.

88plug/searxng-mcp

Plugin Claude Code

Fast, token-efficient MCP for SearXNG metasearch. Privacy-respecting search across 70+ engines with stdio + streamable-http transports, Docker, and optional rendered (Playwright) fetch for JS-heavy pages. Self-hostable. The underlying server is also usable independently of Claude Code via uvx --from git+https://github.

88plug/scientific-method

Plugin Claude Code

Falsification-first investigation workflow for Claude Code: hypothesis ledgers, controlled experiments, adversarial verification, and provable invention.

88plug/scientific-method

Plugin Claude Code

Falsification-first investigation workflow: convert every assertion into a labeled falsifiable hypothesis, predict before measuring, run controlled experiments, verify findings adversarially (REFUTE-first), and persist verdicts in a hypothesis ledger so killed ideas are never re-attacked.

88plug/scientific-method

Agent

Use this agent as one independent seat in a model council — the same question is posed to several seats, each running on a different model (pass a different model override per spawn), blind to each other's answers. The seat investigates with its own read-only probes and returns a structured position with evidence…

88plug/scientific-method

Agent

Use this agent to turn one asserted limit, claim, or candidate root cause into a rigorously designed experiment — without running it. It returns a falsifiable hypothesis with an explicit null, a written probe artifact, a pre-committed outcome→conclusion table, and what each outcome unlocks. Spawn one per hypothesis…

88plug/scientific-method

Agent

Use this agent as the area chair who closes a peer-review round. It receives the submission packet, all independent reviews, the author rebuttal, and any re-scores, then issues the final decision (accept / minor-revision / major-revision / reject) with camera-ready requirements. It weighs evidence quality rather than…

88plug/scientific-method

Agent

Use this agent as one independent reviewer in a peer-review round for an invention, design, finding, or paper-style writeup. Each reviewer gets the same submission packet plus ONE assigned lens (soundness, prior-art/provenance, reproducibility, significance, or fatal-flaw) and works blind to the other reviewers.…

88plug/scientific-method

Agent

Use this agent to evaluate a finding, claimed root cause, performance claim, invention, or research result by attempting to refute it before judging what survives. It returns a verdict (confirmed / prototype / research / kill) with the refutation analysis, calibrated confidence, and a killreason when applicable. Spawn…

88plug/scientific-method

Command

Convene a model council: the same question answered independently across different models, dissent surfaced, cruxes routed to probes.

88plug/scientific-method

Command

Attack an asserted limit, ceiling, or claim with designed experiments.

88plug/scientific-method

Command

Run a full invention campaign: ideate past a limit, refute, build, measure against acceptance criteria, provenance-search, certify.

88plug/scientific-method

Command

Run a full scientific investigation: hypotheses, controlled experiments, verdicts, ledger.

88plug/scientific-method

Command

Create or update the persistent hypothesis ledger (EXPERIMENTS.md) for this project.

88plug/scientific-method

Command

True peer review of an invention/finding/design: blind lensed reviewers, rebuttal, revision, area-chair decision.

88plug/scientific-method

Command

Adversarial REFUTE-first review of current findings/claims before they are trusted.

88plug/scientific-method

Hook

Runs when a session starts on startup, resume, clear and compact, executing surface-ledger.sh via bash. From 88plug/scientific-method.

88plug/scientific-method

Skill Claude CodeCodex

Use this skill whenever someone doubts a number, demands rigorous proof of a cause, or wants something invented and proven — any time a benchmark, metric, ceiling, or root-cause story must be verified rather than trusted, or a limit must be broken with a built, measured mechanism. Typical situations: a measurement…

88plug/screen-mcp

Plugin Claude Code

Eyes and hands on a Linux Wayland desktop over xdg-desktop-portal — screenshot, click, type, scroll, drag, read.

88plug/screen-mcp

Plugin Claude Code

Eyes and hands on a Linux Wayland desktop: screenshot any monitor and click, type, scroll, drag, and read any visible app over xdg-desktop-portal (RemoteDesktop + ScreenCast), with optional OCR + OmniParser icon grounding. Includes screenwatch (1 fps human-eye observe) so agents catch thrashing UIs like people do. Pu.

88plug/screen-mcp

Instructions file

Claude Code instructions for 88plug/screen-mcp, covering claude.md — mcp-screen, how to run / test, invariants & gotchas (don't regress these), conventions and anti-drift (auto-calibrated from real session data).

88plug/screen-mcp

Skill Claude CodeCodex

See and operate the user's real, physical Linux desktop through the mcp-screen MCP — screenshot any monitor and click/type/scroll/drag any visible app. Prefer screenwatch (1 fps) after graphs/maps/canvases/loaders so thrashing UIs are caught like a human watches, not one freeze-frame. Use whenever the user points at…

88plug/screen-mcp

MCP server Claude CodeCodexCursor

MCP server "screen-mcp" as configured in 88plug/screen-mcp. Runs locally from the screen-mcp Python package.

88plug/os-control-mcp

Plugin Claude Code

The sanctioned OS motor cortex for Linux — systemd, journald, logind, D-Bus — with a self-preservation guard.