By mistakeknot
Dynamic statusline for Claude Code — shows workflow phase, bead context, and Codex dispatch state. Integrates with Clavain and interphase.
Dynamic statusline for Claude Code.
interline renders a persistent statusline showing what's happening in your session without you having to check manually. It integrates with multiple sources: beads (active work items with priority coloring), interphase (workflow phase), interlock (multi-agent coordination status), and Clavain dispatch (Codex agent state): and compresses it all into a single line.
Priority coloring makes triage visible at a glance: P0 red, P1 orange, P2 yellow, P3 blue, P4 gray. Each in-progress bead shows its title and phase alongside the priority indicator.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interline
Then run the setup command to install the statusline renderer:
/interline:statusline-setup
JSON config at ~/.claude/interline.json controls colors, layer toggles, labels, and format. The statusline reads from multiple sources and falls back gracefully when optional integrations aren't available: if you don't use interphase, that layer just doesn't render.
scripts/
statusline.sh Main renderer (reads beads, sideband files, dispatch state)
install.sh Installs into Claude Code settings
commands/
statusline-setup.md Setup command
The statusline is not a traditional plugin skill: it's configured as a Claude Code status provider and runs on every prompt.
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 interline[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.
A minimal, opinionated and non-configurable, Claude Code status line
Claude Code statusline showing info at a glance: tokens, context, model, subagents, burn rate, skills, plugins, OpenSpec specs, task lists, and more
Status line with context window, cost, and model info
Real-time statusline HUD for Claude Code - context health, tool activity, agent tracking, and todo progress
Lightweight Claude Code status-line monitor with switchable styles, themes, slash commands, and a local AgentParty bridge for Codex workflows. v3.29.12 keeps the entire AgentParty status block session-correct when several sessions share one project: channel, identity, unread count, message preview, and listener state now come from the matching config-owned cache slot. Claude Code remains the full native statusLine data source for quota/session/context/cache/activity fields; Codex support is the local AgentParty presence bridge and never calls AgentParty, renders or transmits tokens, makes network requests, or adds OpenAI quota accounting. v3.29.6 adds a depletion ETA to a maxed projection (`→100%·1h12m`) and stops calling a quiet-channel listener "down" while its process is alive. v3.29.5 makes launchd/systemd-spawned daemons recognizable to `cs daemon stop` and the upgrade drift-kill (they were unkillable), and stops an exiting daemon from deleting the current owner's pidfile. v3.29.4 makes `cs upgrade` the single documented upgrade path and fixes the daemon's silent auto-upgrade failure under launchd/systemd (uv/pipx not on the service PATH). v3.29.3 fixes the same respawn loop on Linux/systemd (Restart=on-failure) and reads the new AgentParty listener.mentions_only contract field instead of probing argv. v3.29.2 stops launchd from respawning a redundant daemon every 10s and cuts warm render time from ~6ms to ~2.4ms. v3.29.1 fixes a daemon crash on any render slower than the tick interval (a negative time.sleep()) — the reason the daemon kept dying and never picked up upgrades. v3.29.0 redesigns the AgentParty block (monochrome glyphs, listening state stated outright, last message on its own line with unread/@mention markers) and fixes the listener heartbeat field that made every live listener render as `down`, plus three daemon defects that kept an upgrade from reaching the running daemon. Requires the cs CLI from PyPI (pip install claude-statusbar or uv tool install claude-statusbar).
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses