Self-managing documentation system with hierarchical structure, intelligent automation, pattern discovery, and agent orchestration
Deprecate/retire a doc — move it into archive/ (reversible, link-safe), or list archival candidates
Brief the LLM on hit-em-with-the-docs' surface (commands, primitives, frontmatter contract, knowledge-base workflow) and orient the user.
Audit knowledge-base facts for staleness; optionally re-verify a specific fact
Insert a cites: entry for a fact into a playbook's symptoms block
Manage custom documentation domains (list | add | remove) beyond the built-in 15
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A self-managing documentation system that keeps your docs organized, accurate, and easy to find.
[!IMPORTANT] You still need to remember to use this plugin when creating documentation! As projects grow, documentation needs to be created and maintained. You'll need to invoke this plugin or ask an LLM to create documentation for your features, workflows, or infrastructure. This plugin must be invoked to create, update, or maintain your docs.
[!NOTE] 2.5.0 — INDEX/REGISTRY regeneration fix.
integratecould only append a row to an INDEX.md that already had a table, so the first document into any domain was never registered — and the failure was silently swallowed.integrateandmaintainnow rebuild domain + rootINDEX.md/REGISTRY.mdfrom the documents on disk via the real generators. Newhewtd index(aliasreindex) command regenerates all indexes on demand;maintainself-heals them every run;auditgains anindex-driftrule that--strictgates CI on. Closes #7. See CHANGELOG.2.4.0 —
migrate-incidentpath bug fix + recovery command.migrate-incidentnow correctly writes to<vault-root>/incidents/<slug>/(the locationhewtd maintain's incidents-index generator scans). In 2.3.0 the target was derived from the source flat file's parent dir, which silently bypassed the canonical layout when the flat file lived at the vault root. Newhewtd fix-legacy-layoutcommand relocates 2.3.0-buggy folders and rewrites factprovenance:refs. Idempotent, dry-run supported. See CHANGELOG.New in 2.3.0: the knowledge-base primitives layer. Three new tiers (
fact,incident-narrative,incident-facts) for citable atomic claims and immutable postmortems, plus an optionalsymptoms:frontmatter field on any-tier playbooks for symptom→playbook routing withcites:to facts. Three new deterministic indexes (facts/INDEX.md,incidents/INDEX.md,symptoms/INDEX.md) auto-generate onhewtd maintainwhen a vault root exists. Five new CLI commands:find-citers,audit-facts [--run-verify],extract-facts,cite,migrate-incident. Newaudit --strictflag for CI gating. New/hit-em-with-the-docs:helpslash command for LLM orientation. Four authoring templates attemplates/knowledge-base/. Full reference:docs/knowledge-base-primitives.md. Agent guide:docs/LLM-GUIDE.md.New in 2.2.0: the
tierenum gains a"plan"value for persistent-planning lg-mode artifacts (phase / task / atom / notes documents), and theversionandstatusfields are now conditionally relaxed for plan-tier docs (plans use lifecycle status, not semver). Existing tiers (guide / standard / example / reference / admin) are unchanged. Seedocs/plan-tier-frontmatter.mdfor the full reference.
When projects get bigger, documentation becomes a mess. Important information gets lost across many files, links break when you move things around, and nobody knows if the docs are still correct. Hit 'Em With The Docs fixes these problems by organizing everything into 15 clear categories, automatically checking your links, and making sure every document has the right information tags. The system watches your docs and fixes common problems without you having to do it manually. Everything stays organized and up-to-date so your team can find what they need fast.
The plugin creates a special folder called .documentation in your project with 15 organized sections called "domains" - things like security, API docs, database guides, and testing information. When you add a document, the system reads it and figures out which category it belongs in based on keywords and content. Each document gets special information tags (metadata) added to the top - things like the title, what category it's in, when it was last updated, and how long it takes to read. This metadata helps both you and the system understand what each document is about.
npx claudepluginhub theglitchking/hit-em-with-the-docsGenerate production-quality SVG technical diagrams (architecture, flowchart, UML, ER, sequence, etc.) with 7 built-in styles. Export as SVG+PNG via @resvg/resvg-js.
Bash Loop operating mode for Claude Code - action over explanation, tight feedback loops, intelligent context preservation, and graceful subagent control
Autonomous loop engine with orchestrated subagents, DAG-based task execution, context persistence across iterations, and intelligent failure recovery with circuit breaker
Eliminate context rot in Claude Code with intelligent memory hierarchy, auto-learning hooks, and specialized subagents. 8-layer architecture with SessionStart/End hooks and MCP knowledge base.
Polyglot progressive linting for monorepos — adapter-driven baselines, per-app drift detection, and idempotent skips. Supports JavaScript/TypeScript (ESLint, Biome), Python (Ruff), Go (golangci-lint), Rust (Clippy), Terraform/OpenTofu (tflint), and Ansible (ansible-lint).
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.