By jingtaozf
Literate-programming rules, skills, and hooks for AI agents. Dual-audience documents that work for both human readers and AI agents.
Run the project's literate-programming verification — tangle + structure check + smoke test. Reports any violations of the four-part section shape or prose discipline.
Audit a PR diff (or recent git history) for cowork-specific drift modes — sycophancy patterns, tone drift, convergent regression, citation hallucination, stake mismatch. Reports findings grouped by rule.
Research-grounded structural audit of one literate `.org` file or a whole project tree. Checks for the anti-patterns the transfer-gradient research identifies — phase-name headings, missing :CUSTOM_ID: anchors on multi-referenced sections, missing prose-before-src, sections with no stable anchor for cold-start retrieval, typographic-only load-bearing affordances. Reports violations grouped by rule.
Audit one .org file's prose against the lp-prose-no-self-narration rule. Reports paragraphs that fail the deletion test (self-narration, filler parentheticals, mechanism-without-action). User-invocable only — do NOT auto-trigger on every edit.
Prose drives code in any literate-programming repo. Use BEFORE editing any .org file in a project that follows literate-programming discipline. Auto-activates when the user asks for a feature, change, refactor, or fix in .org files, and when they say "explain", "document", "draft a section", "write up", "rationale".
Run the 6-point dual-audience checklist on a literate .org section. Each item maps to a research-backed LP rule (heading-as-concept, :CUSTOM_ID: for ≥2 refs, WHY in prose, one mechanism per section, structural-not-typographic affordances, cold-start agent recoverability). Use after editing or writing an .org section, or as a manual review pass.
Elisp-specific literate-programming caveats — lexical-binding handling, macro re-expansion, reload discipline. Auto-activates when editing .el files or literate .org files with Elisp src blocks. Consult before adding lambdas in callbacks/timers, before changing macro definitions, or after editing a literate-elisp .org.
Python-specific literate-programming traps — tangle path resolution, ruff formatter file-local-var, noweb refs for big classes, byte-equivalence gate, bare-* parser trap. Auto-activates when editing .py files or literate .org files with Python src blocks. Consult before renaming .org files (tangle paths break), before adding new tangle targets, or after editing a literate-python .org.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
npx claudepluginhub jingtaozf/literate-agent --plugin literate-agentLiterate-programming rules, skills, and hooks for AI agents. Dual-audience documents that work for both human readers and AI agents.
Emacs integration SDK for Claude Code - org-mode AI blocks, streaming responses, and MCP server
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
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).
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.