Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Knowledge compounding — durable pattern repository with provenance tracking, temporal decay, and semantic retrieval via qmd.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin interknowKnowledge compounding for Claude Code.
interknow is a durable pattern repository — it stores lessons learned from code reviews, debugging sessions, and architectural decisions so they compound across sessions instead of being forgotten.
Each knowledge entry is a markdown file with YAML frontmatter tracking provenance (independent vs primed), domain tags, evidence anchors (file paths, commit SHAs), and a lastConfirmed timestamp. Entries that go 10 reviews without independent confirmation decay to archive, preventing stale knowledge from polluting future sessions.
The plugin includes a qmd MCP server for semantic search across entries, so you can ask "what do we know about database migrations?" and get relevant entries ranked by similarity.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interknow
Compound a new pattern after solving a problem:
/interknow:compound
Or ask naturally:
"document what we just learned about SQLite WAL mode"
"save this debugging pattern for next time"
Query existing knowledge:
/interknow:recall
Or:
"what do we know about shell portability?"
"recall knowledge about hook timing"
config/knowledge/
*.md Knowledge entries (markdown + YAML frontmatter)
archive/ Decayed entries
README.md Entry format, provenance rules, decay rules
scripts/
launch-qmd.sh qmd MCP server launcher (graceful degradation)
skills/
compound/SKILL.md Knowledge entry creation workflow
recall/SKILL.md Knowledge query workflow
hooks/
session-start.sh Reports knowledge stats at session start
---
title: Shell stat fallback to epoch zero
domain: shell
provenance: independent
lastConfirmed: 2026-02-20
evidence:
- path: os/clavain/lib/lib-sprint.sh
line: 142
---
When `stat` fails on a missing file, fall back to epoch 0 (not current time).
Using current time would skip all staleness checks...
interknow was extracted from interflux's knowledge layer. interflux's launch-qmd.sh is now a stub that redirects here.
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Personal knowledge graph for Claude Code — remembers decisions, searches past work, captures sessions
The memory layer Claude Code doesn't have. A persistent knowledge graph that learns from your conversations — your AI assistant never starts a session blind.
Governed team memory — deterministic policy, lifecycle, team sharing via qmd
Persistent memory system for Claude Code with SQLite, FTS5, and vector search
Shared knowledge commons for AI agents; find, share, and confirm collective knowledge to stop rediscovering the same failures.
Memory compression system for Claude Code - persist context across sessions
[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.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
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-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.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
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