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-stategit 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-state)<a href="https://agentmods.dev/skills/trentisiete/endy/endy-state"><img src="https://agentmods.dev/badge/skills/trentisiete/endy/endy-state/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-state"><img src="https://agentmods.dev/badge/skills/trentisiete/endy/endy-state.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 | $0.00111 | $0.02353 |
| Opus 5 | $0.00056 | $0.01177 |
| Sonnet 5 | $0.00022 | $0.00471 |
| Haiku 4.5 | $0.00011 | $0.00235 |
Grade A, and why
endy-state scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
endy-state — Inspect endy environment
endy state builds a snapshot of where the current task sits inside the endy multi-agent stack: handoff chain, peers, tier headroom. It is read-only — never spawns anything, never touches tmux state.
When to use
- You're mid-task and considering a handoff. Run
endy stateto see which agents still have headroom (codex 5h+wk, opencode $/session) before picking--to. - You're an agent that just received a handed-off task. The
## endy environmentblock at the top of your prompt is the same data — but if you want it again on turn N, re-runendy stateinstead of re-reading the prompt. - You want the JSON for a dashboard or a smoke test.
--format jsonis the stable contract.
Three formats
endy state # human-readable, default
endy state --format human
endy state --format json
endy state --format prompt # the '## endy environment' block
--task-id <id> lets you inspect any task, not just self. Without it, state.py self-detects via $TMUX_PANE → tmux window name → task-<id>. If invoked outside tmux (no pane), the self block is omitted but peers/tiers still render.
What you get
endy state
==========
task: 20260515-142312-a1b2 agent: claude
session: endy-noetiklab cwd: /Noetiklab
orchestrator: demo (codex)
handoff chain (3rd link is you):
1. codex — codex rate limit (5h window exhausted)
2. gemini — gemini daily quota exhausted
3. claude ← you
reason: "gemini daily quota exhausted"
peers:
same session: opencode on task-20260515-141100-9f02
other session: endy-other-project (2 task windows)
tier headroom:
codex: plus 5h 87% wk 91% resets at 2026-05-15T17:10:00Z
opencode: $0.42 session model: claude-opus-4-7
claude: max estimate-only
gemini: unknown
hermes: unknown
cmd: unknown
The unknown source on a tier means we have no signal for it yet — a
future expansion will add stderr-detected fallbacks (this is part of
Phase 4 in the project roadmap: auto-detection
of exhaustion from CLI stderr signals). Don't assume an unknown tier
is exhausted — assume nothing.
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.
- 10d ago First seen · 182 lines · 111 tokens per session scan A de9ad4f771d4
endy-state is a skill published in the GitHub repository trentisiete/endy (7 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 2,353 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. 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.