By mistakeknot
Documentation quality toolkit — enforces CLAUDE.md/AGENTS.md boundaries, applies progressive disclosure, deduplicates across doc hierarchy.
Documentation quality toolkit for Claude Code projects.
interscribe enforces a single rule: CLAUDE.md is for Claude Code configuration only (plugins, hooks, tool preferences, permissions), and everything else — architecture, workflows, conventions, troubleshooting — belongs in AGENTS.md. Project knowledge that leaks into CLAUDE.md wastes context tokens on every session start and fragments the information agents need to do their jobs.
The plugin has three modes. Audit analyzes your docs and reports a health score: boundary violations, token budgets, duplicate instructions, stale references. Refactor fixes what it finds automatically — moves project knowledge from CLAUDE.md to AGENTS.md, extracts oversized AGENTS.md sections into docs/ reference files with backlinks, removes duplicates, and cleans up dead links. Consolidate works across your full doc hierarchy (global → project → subproject) to deduplicate instructions that appear at multiple levels.
Refactoring is fully automatic. All changes are reviewable via git diff. The philosophy is: trust the tool, review the output.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interscribe
Audit your project's documentation health:
/interscribe audit
Automatically restructure docs for progressive disclosure:
/interscribe refactor
Deduplicate across your doc hierarchy:
/interscribe consolidate
Target a specific path:
/interscribe audit apps/autarch
skills/interscribe/ Main skill — audit, refactor, consolidate modes
scripts/ audit-docs.sh (line/token metrics), find-duplicates.sh (heading overlap)
docs/canon/ convention for foundational project docs (PHILOSOPHY.md, naming, doc standards)MIT
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 mistakeknot/interagency-marketplace --plugin interscribe[DEPRECATED — use intervox] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervox (via the interim intervoice), which adds a measured stylometric fingerprint, LLMism linter, and verified closed-loop apply on top of the global multi-register profile.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 57 commands, 20 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Multi-agent review and research with scored triage, domain detection, content slicing, intermediate finding sharing, and knowledge injection. 17 agents (12 review + 5 research), 8 commands (incl. flux-melange — a goal-seeking adaptive review loop with lens fusion and novelty/risk/taste scoring), 3 skills (flux-engine, flux-review-engine, flux-melange-engine), 2 MCP servers (exa, openrouter-dispatch). Companion plugin for Clavain.
Optimize CLAUDE.md and docs/ ecosystem following Boris Cherny's best practices
CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Optimize your CLAUDE.md hierarchy — deduplicate, detect misplacement, compress bloat, and visualize token usage across global/project/repo levels
Documentation and authoring workflow router: audit docs vs code drift, sync docs after changes, optimize prompts and SKILL.md files, validate GLFM and Markdown formatting, summarize files/URLs/images with fidelity enforcement. Use when: docs are out of date, CLAUDE.md needs improving, SKILL.md needs optimizing, checking if documentation matches code, summarizing files or URLs.
llmdoc Claude Code plugin with init, commit-watermark update detection, update modes, temporary investigation cache, and use