Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Agent and agency naming for legible orchestration — memorable, deterministic identities across all surfaces.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin internameMemorable names for agents and agencies. Because "fd-safety reviewing auth.go" tells you nothing, but "Lapsed Pacifist reviewing auth.go" you'll remember tomorrow.
When Demarch dispatches five review agents in parallel, you need to know who's doing what at a glance. Technical IDs like fd-safety and fd-correctness are functional but forgettable. Intername assigns each agent a permanent, distinctive display name that appears consistently across every surface: dispatch tables, tmux panes, trust reports, verdict attributions, and TUI dashboards.
Names are deterministic — fd-safety is always "Lapsed Pacifist", in every project, every session. You build recognition over time. After a few reviews you'll know that "Lapsed Pacifist" is the security reviewer and "Conditions Apply" checks correctness, without reading the fine print.
Four theme packs ship out of the box. Switch freely; your custom overrides layer on top of any theme.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install:
/plugin install intername
Look up a name:
/intername:name fd-safety
fd-safety → Lapsed Pacifist (theme: culture)
List all agent names:
/intername:name --list
AGENT TYPE DISPLAY NAME
fd-architecture Fair Warning
fd-correctness Conditions Apply
fd-game-design Playing Both Sides
fd-performance Whose Idea Was This
fd-quality Conditions Of Satisfaction
fd-safety Lapsed Pacifist
...
Switch themes:
/intername:name-theme demarch
Theme switched: culture → demarch
Sample names:
fd-safety → Sentinel (was: Lapsed Pacifist)
fd-correctness → Arbiter (was: Conditions Apply)
flux-drive → Threshold Caucus (was: The Difficult Second Album)
Dry wit, polite menace, and bureaucratic absurdity — inspired by Iain M. Banks' Culture ship names.
The Difficult Second Album dispatching... Lapsed Pacifist reviewing auth.go... Fair Warning found 3 findings... Conditions Apply checking data layer...
Boundary concepts, diplomatic terms, and liminal vocabulary — reflecting the inter-* philosophy of the space between things.
Threshold Caucus dispatching... Sentinel reviewing auth.go... Surveyor found 3 findings... Arbiter checking data layer...
Short, distinctive, unambiguous — NATO phonetic alphabet with adjective modifiers. Maximum UI compatibility.
Strike Victor dispatching... Red Bravo reviewing auth.go... Steady Foxtrot found 3 findings... Sharp Charlie checking data layer...
Your own names. Add entries to data/themes/custom.json — they override any active theme.
{
"agents": {
"fd-safety": "My Security Buddy"
}
}
export INTERNAME_DISABLED=1
All consumers fall back to raw agent IDs. Unset the variable to re-enable.
Agencies and agents get permanent, globally stable names. Dispatches inherit the agent name plus a sequence number. Project context is shown alongside the name, not encoded into it:
┌── The Difficult Second Album (███ 4/7) ──────────────────┐
│ Lapsed Pacifist (1/3) │ reviewing auth.go │
│ Conditions Apply (1/2) │ reviewing api.go │
│ Fair Warning │ ✓ done (3 findings) │
└──────────────────────────────────────────────────────────┘
The naming library (hooks/lib-naming.sh) is sourced by consumers — it's not a hook or MCP server. If intername isn't installed, consumers fall back silently to raw IDs.
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Marketplace for the Agency CLI - an AI agent orchestrator
Use proactively for generating creative non-olympian Greek god names with rich backstories, mythological authenticity, and modern accessibility for storytelling projects
Automatically detects and loads AGENTS.md files to provide agent-specific instructions alongside CLAUDE.md. Enables specialized agent behaviors without manual intervention.
Git-backed messaging for AI agent coordination across sessions, worktrees, and machines.
5つの専門エージェント(ブランディング・商標・デジタルプレゼンス・国際展開・コンテキスト管理)がチームで相互フィードバックしながら議論し、最適なアプリ名を決定する
Repowire mesh usage skills for AI coding agents: cross-agent review and planning, delegate, usage patterns, and install/update. Backend-agnostic and parameterised on the agent you choose.
[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