By mistakeknot
Phase tracking, gate validation, and work discovery for the Beads issue tracker. Companion plugin for Clavain — adds lifecycle state management on top of the core beads plugin.
Phase tracking and gate validation for the Beads issue tracker.
interphase adds lifecycle state management on top of beads: discovery, planning, building, review, shipping. Each phase has gates that should be satisfied before moving to the next one. By default, interphase tracks and reports without blocking (observability-first). An opt-in strict mode can fail closed for high-risk transitions.
The libraries (lib-phase.sh, lib-gates.sh, lib-discovery.sh) are sourced by consuming plugins like Clavain rather than running as standalone hooks. This keeps the hook budget lean while still making phase awareness available everywhere it's needed.
Phase state is communicated to interline via sideband files at ~/.interband/interphase/bead/${session_id}.json, so the statusline can show your current workflow phase without any direct coupling between the plugins.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interphase
Companion plugin for Clavain: most useful when installed alongside the core engineering plugin.
The beads-workflow skill provides guidance for the full beads lifecycle:
"what phase am I in?"
"check gate requirements for review"
"discover open work"
lib/
lib-phase.sh Phase state tracking (set/get/infer)
lib-gates.sh Gate validation with dual persistence
lib-discovery.sh Work discovery scanner
skills/
beads-workflow/ Lifecycle guidance skill
tests/ Bats shell tests
By default, functions are fail-safe: return 0 on dependency/error paths and avoid blocking workflow. In strict mode, hard-tier transitions can intentionally fail closed.
interphase supports an opt-in strict gate mode for high-risk transitions:
CLAVAIN_GATE_FAIL_CLOSED=true to enable strict behavior.P0/P1).CLAVAIN_SKIP_GATE="reason" remains available as an emergency override and is explicitly audited.CLAVAIN_DISABLE_GATES=true still bypasses all gate enforcement.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 mistakeknot/interagency-marketplace --plugin interphase[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.
Plan-only mode and GitHub-issue-to-Beads workflow. Provides planning without auto-execution and structured work decomposition into Beads epics, tasks, and sub-tasks with verifiable acceptance criteria.
Ambient awareness of Fabrik (the GitHub-Project-driven SDLC pipeline orchestrator) for the human's interactive Claude Code session. Turns Claude into a product-management buddy and supervisor for projects that use Fabrik to automate issue processing.
Superpowers skills + Beads issue tracking for Claude Code, Codex, OpenCode, and 6 more AI coding agents. Composable skills + persistent task memory.
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.