Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add trentisiete/endy --skill endy-livegit clone --depth 1 https://github.com/trentisiete/endyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/trentisiete/endy/endy-live)<a href="https://agentmods.dev/skills/trentisiete/endy/endy-live"><img src="https://agentmods.dev/badge/skills/trentisiete/endy/endy-live/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/trentisiete/endy/endy-live"><img src="https://agentmods.dev/badge/skills/trentisiete/endy/endy-live.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.07350 |
| Opus 5 | $0.00051 | $0.03675 |
| Sonnet 5 | $0.00021 | $0.01470 |
| Haiku 4.5 | $0.00010 | $0.00735 |
Grade B, and why
endy-live scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Or settings in `~/.gemini/settings.json` (auth method + provider). How it starts
The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
endy-live — Interactive agent pane orchestration (primary skill)
This skill is the principal one for working inside the endy stack. If your task is "open a CLI, talk to it, manage it" — start here.
Pair with endy-delegate only when you need to hand off work between
agents (endy handoff) or fire a fully headless batch (endy spawn).
For everything else — interactive sessions, model switching, picker
navigation, auth, slash commands — this is the skill.
When to use live vs spawn
Use endy live when… |
Use endy spawn when… |
|---|---|
| You want to see the agent's live output | You just need the final result |
| You may correct or redirect mid-task | The task is fire-and-forget |
| The agent has menus or interactive prompts | The agent runs a single prompt to completion |
| You want the user watching real-time state | You want log-based tracking only |
| Short inspection/verification tasks | Long autonomous multi-turn work |
Operations
open — Launch an agent in a named tmux window
endy live open <name> <agent> [--cwd <dir>] [--model <m>] [--persona <p>] [--full-auto]
<name>— meaningful name chosen by you (e.g.,claude-review,cmd-design)<agent>— one of:claude,cmd,opencode,hermes,codex,gemini,bash
The window is a real interactive terminal: the agent owns the pty, draws its TUI normally, can launch its own subagents/commands, and you drive it via send/capture. Output is mirrored to .logs/.../live-<name>.log via tmux pipe-pane (does not interfere with the TUI). Use bash (alias shell) when you just want a raw shell window — handy as a generic subagent terminal where you run commands manually.
--cwd— working directory for the agent (default: current directory)--model— model override (agent-specific: supported by claude/opencode/hermes)--persona— persona/skill name (opencode:--agent, hermes:--skills)--full-auto— skip permission prompts (--yolofor cmd/hermes,--dangerously-skip-permissionsfor claude/opencode)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 664 lines · 103 tokens per session scan B a4d51b6a945c
endy-live is a skill published in the GitHub repository trentisiete/endy (7 stars, last pushed 3mo ago), licensed MIT. It adds 103 tokens to every session and 7,350 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
go
Approve and execute the exact Hames contract just presented in the same session, or resume a selected active contract, when the user invokes /go.
setup
Configure or diagnose Hames in the current project when the user invokes /setup.
ready
Prepare and present a bounded task contract for same-session approval by /go when the user invokes /ready.
doctor
Diagnose a Hames installation without changing it when the user invokes /doctor.
context-rot-cleanup
Examine workspace files for durable context, filter out low-value noise, and clean up stale memory or rule files that contribute to context rot.
commander-memory-cleanup
Distill Herd commander memory, clean stale MEMORY.md entries, promote durable commander lessons into LONGTERMMEM.md, and propose shared-knowledge updates through a review gate. Use for periodic commander memory cleanup.