{"name":"88plug-88plug","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"88plug-recover-from-false-positive","source":{"source":"github","repo":"88plug/recover-from-false-positive"},"description":"Recover Claude Code sessions after an Anthropic API output-classifier false positive (the \"cyber-related safeguards\" / \"appears to violate our Usage Policy\" hard failure). A JSON-aware .jsonl log surgeon that surgically removes the triggering message + refusal turn and re-stitches the parentUuid chain so the session resumes cleanly, cleans accumulated refusals across old sessions, and installs a per-repo CLAUDE.md framing guard to stop recurrence.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","classifier","false-positive","session-recovery","jsonl","log-repair","usage-policy","content-filter","refusal-recovery"],"category":"productivity"},{"name":"88plug-amnesia-plugins-amnesia","source":{"source":"git-subdir","url":"https://github.com/88plug/amnesia","path":"plugins/amnesia"},"description":"Seamless context continuity across Claude Code compaction. Four background layers (continuous tool-call capture, mechanical PostCompact handoff, async Opus 4.7 enrichment at --effort max, async Stop-hook refinement, and preemptive snapshot before the next compact) keep the agent's working state intact across every compaction and resume. All summarization is isolated from CLAUDE.md/auto-memory and invisible to the user.","version":"0.3.1","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","mcp","mcp-server","model-context-protocol","context","compaction","memory","continuity","session-continuity"],"category":"productivity"},{"name":"88plug-caveman-plus","source":{"source":"github","repo":"88plug/caveman-plus"},"description":"Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","token-compression","communication-mode","caveman","prompt-engineering","context-efficiency","terse","output-style","cost-saving"],"category":"productivity"},{"name":"88plug-total-recall","source":{"source":"github","repo":"88plug/total-recall"},"description":"Cross-session, cross-CLI memory for AI coding assistants. Mines transcripts from 10 supported CLI clients. Surfaces operator identity / decisions / bans / corrections / goals / voice via 26 MCP tools, 6 hooks (SessionStart signpost + SessionStart compact-restore + UserPromptSubmit retrieval + Stop/PostCompact re-index + PreCompact continuity-seed), 15 slash commands, and 3 skills. gte-modernbert hybrid recall; worktree-aware project scoping; post-compaction coding-continuity packet. Optional local-LLM refinement ([llm] extra, ollama, off by default). The operator becomes the source of truth; the model stops re-asking what they already told it.","version":"2.3.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","mcp","mcp-server","model-context-protocol","memory","recall","cross-session","operator-profile","data-mining"],"category":"productivity"},{"name":"88plug-searxng","source":{"source":"github","repo":"88plug/searxng-mcp"},"description":"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.com/88plug/searxng-mcp searxng-mcp`.","version":"0.2.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","mcp","mcp-server","model-context-protocol","search","searxng","metasearch","privacy","self-hosted","uvx"],"category":"productivity"},{"name":"88plug-deepwiki","source":{"source":"github","repo":"88plug/deepwiki"},"description":"Talk to any public GitHub repo's auto-generated documentation via Cognition's hosted DeepWiki MCP. Read-only research into codebases without cloning. Note: this plugin wraps a remote MCP server hosted by Cognition AI at mcp.deepwiki.com; 88plug does not operate the underlying service.","version":"0.1.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","mcp","mcp-server","model-context-protocol","deepwiki","documentation","github","research","cognition","codebase"],"category":"productivity"},{"name":"88plug-scientific-method","source":{"source":"github","repo":"88plug/scientific-method"},"description":"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","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","scientific-method","investigation","debugging","hypothesis","falsification","experiment","root-cause","benchmarking"],"category":"productivity"},{"name":"88plug-drive-remote-terminal","source":{"source":"github","repo":"88plug/drive-remote-terminal"},"description":"Operate and observe an interactive full-screen TUI on a REMOTE machine over tmux/screen + SSH by driving it like a human: type with send-keys, screenshot with capture-pane, in a type-wait-screenshot-read loop. For the Claude Code TUI, vim, top, curses installers, REPLs, or any program that needs a real PTY over SSH.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","tmux","screen","ssh","tui","remote","terminal","pty","headless"],"category":"productivity"},{"name":"88plug-project-prospector","source":{"source":"github","repo":"88plug/project-prospector"},"description":"Discover, catalog, and rank everything you've built or sketched on a machine via a two-pass parallel read-only sweep: a clustered project catalog plus blind-spot agents (transcripts, other agent CLIs, running services, research artifacts, beyond-home), synthesized into a tiered novelty/leverage ranking with idea/live/dormant tags and evidence-anchored rationale.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","project-discovery","catalog","ranking","filesystem-audit","novelty","read-only","multi-agent","inventory"],"category":"productivity"},{"name":"88plug-screen-mcp","source":{"source":"github","repo":"88plug/screen-mcp"},"description":"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. Pure-Python, CPU-only. GNOME/Wayland only. Ships the MCP server plus a drive-screen skill that encodes the locate-ground-act-confirm loop.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","mcp","mcp-server","model-context-protocol","wayland","gnome","screenshot","desktop-automation","ocr"],"category":"productivity"},{"name":"88plug-os-control-mcp","source":{"source":"github","repo":"88plug/os-control-mcp"},"description":"The sanctioned OS 'motor cortex' for an agent on a Linux box: control systemd services/timers, query journald, read host resources/processes, send desktop notifications, drive D-Bus, and manage power (suspend/reboot/poweroff) — all through structured interfaces (systemctl/loginctl/journalctl/busctl), never raw PID hacks. Pure standard library, zero pip deps. A self-preservation guard refuses severing actions on units the agent depends on (dbus, logind, sshd, network, tailscaled, the session, goosed) unless force=true. Ships the MCP server plus a control-os skill. The system-service counterpart to screen-mcp's GUI control.","version":"2026.6.25","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","devops","automation","claude-code-plugin","claude-skills","mcp","mcp-server","model-context-protocol","linux","systemd","dbus","journald","logind","system-administration"],"category":"productivity"},{"name":"88plug-use-latest-version","source":{"source":"github","repo":"88plug/use-latest-version-mcp"},"description":"Stop suggesting stale package versions from training data. 15 MCP tools over 39 package registries (npm, PyPI, Maven, crates.io, Go, RubyGems, NuGet, Packagist, Docker/GHCR/Quay/GCR, Hex, pub.dev, CRAN, Homebrew, and more): latest-version + package-info lookups, semver compare, install-command generation, batch checks, project dependency scanning, outdated reports, conflict detection, compatibility checks, and a scan -> optimize -> validate -> apply upgrade pipeline that edits manifests with dry-run + automatic backups by default. Local-first, no API key required (an optional GITHUB_TOKEN raises GitHub rate limits).","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","mcp","mcp-server","model-context-protocol","package-versions","dependencies","npm","registries","outdated","semver"],"category":"productivity"},{"name":"88plug-deepwiki-index","source":{"source":"github","repo":"88plug/deepwiki-index"},"description":"Index a public GitHub repo's DeepWiki (the page the 'Ask DeepWiki' badge links to) hands-free, and do it autonomously after publishing or updating a repo — no human clicking. Encodes the verified deepwiki.com trigger (api.devin.ai/ada/index_public_repo, reCAPTCHA v2-invisible) and the trusted-browser path: drive the real desktop browser (screen-mcp) or run the bundled Playwright helper with a real Chrome profile so the captcha passes silently, then poll the public status API to completed.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","deepwiki","documentation","indexing","github","wiki","recaptcha","devin","repo-indexing"],"category":"productivity"},{"name":"88plug-addlightness","source":{"source":"github","repo":"88plug/addlightness"},"description":"Simplify, then add lightness. Removes AI-generated code fat while preserving functionality, then benchmarks the speedup. Multi-pass: measure weight -> trim -> verify equivalence -> benchmark.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","code-quality","refactoring","performance","benchmarking","dead-code","complexity","code-weight","ai-code-cleanup"],"category":"productivity"},{"name":"88plug-drift-detector","source":{"source":"github","repo":"88plug/drift-detector"},"description":"Detects when Claude drifts away from your active output contract (a terse persona, hard formatting/length rules, an in-character voice) and quietly steers it back. Each assistant turn is scored by a deterministic, dependency-free engine; a status-line badge shows live drift and the next prompt gets a one-shot correction nudge when the previous reply broke contract.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","mcp","mcp-server","model-context-protocol","drift-detection","guardrails","instruction-following","llm-monitoring","persona"],"category":"productivity"},{"name":"88plug-trigger-my-training","source":{"source":"github","repo":"88plug/trigger-my-training"},"description":"A ground-first reflex: the agent judges (from its own training, any domain) when a request is complex/irreversible, grounds before acting, and is hard-blocked from the destructive step until it has.","version":"1.0.0","strict":true,"keywords":["claude-code","claude","anthropic","ai","llm","ai-agents","developer-tools","productivity","automation","cli","claude-code-plugin","claude-skills","agent-safety","guardrails","grounding","preflight","irreversible-actions","reasoning","infrastructure","safety"],"category":"productivity"}]}