Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin interdoc- Added change-set update mode, coverage report, and style lint triggers
There is **no source code** to build or test. The "implementation" is the skill documentation and shell scripts.
After generation/update, interdoc sends AGENTS.md to Oracle for independent critique.
> Cross-AI documentation for interdoc. Works with Claude Code, Codex CLI, and other AI coding tools.
Recursive AGENTS.md generator for Claude Code.
Point interdoc at a project and it produces cross-AI compatible documentation: AGENTS.md files that work with Claude Code, Codex CLI, and whatever comes next. It spawns parallel subagents to analyze each directory, consolidates their findings, deduplicates cross-cutting patterns, and shows you a unified diff before writing anything.
Why AGENTS.md? Claude Code reads both AGENTS.md and CLAUDE.md, but AGENTS.md is the cross-AI standard. Using it as the primary format means your documentation works regardless of which agent you're running.
The skill auto-detects mode: no AGENTS.md means generation (full recursive pass), existing AGENTS.md means update (incremental changes only, preserving what you've already written).
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interdoc
Or manually:
git clone https://github.com/mistakeknot/interdoc.git
cd interdoc && /plugin install .
Ask naturally: interdoc picks up the intent:
"generate documentation for this project"
"update AGENTS.md"
"fix stale references"
Generation: spawns one subagent per directory in parallel, each analyzing purpose/architecture/conventions/gotchas, then consolidates into coherent docs with cross-references. For large projects (100+ files), it offers scoping: top-level only, full recursive, or custom.
Update: detects git changes since last update, skips up-to-date directories, and proposes incremental additions/modifications/deletions rather than full rewrites. Shows exact diffs in unified diff format.
Fix: deterministic structural repairs (broken cross-links from renames, deletions, moves) without spending LLM tokens. Use /interdoc fix after reorganizing files.
CLAUDE.md harmonization: if you have both CLAUDE.md and AGENTS.md, interdoc can consolidate them: migrates project docs to AGENTS.md, slims CLAUDE.md to settings only, adds a pointer.
After generating docs, interdoc automatically sends them to Oracle for independent critique via Oracle. This catches blind spots that self-review misses. Never blocks if Oracle is unavailable: the feature is additive, not required.
Add "dry run" to your request to preview without writing. Apply later with "apply last preview" (valid until HEAD changes).
skills/interdoc/SKILL.md Main skill definition
hooks/ SessionStart (check freshness), PostToolUse (commit check)
.claude/agents/ interdocumentarian.md (specialized directory analyzer)
MK (mistakeknot@vibeguider.org)
MIT
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Make a codebase agent-ready by scaffolding AGENTS.md, ARCHITECTURE.md, and docs/ structure following progressive disclosure patterns. Creates CLAUDE.md as a symlink for Claude Code compatibility.
Generate and maintain AGENTS.md, copilot-instructions.md, and other agent rule files
llmdoc Claude Code plugin with init, update modes, temporary investigation cache, and use
CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
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, 52 commands, 19 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.
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), 7 commands, 1 skill (unified flux-drive with review/research modes), 2 MCP servers (exa, openrouter-dispatch). Companion plugin for Clavain.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim