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 2JIHAN/show-me-your-eta --skill turn-etagit clone --depth 1 https://github.com/2JIHAN/show-me-your-etaWrote 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/2jihan/show-me-your-eta/turn-eta)<a href="https://agentmods.dev/skills/2jihan/show-me-your-eta/turn-eta"><img src="https://agentmods.dev/badge/skills/2jihan/show-me-your-eta/turn-eta/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/2jihan/show-me-your-eta/turn-eta"><img src="https://agentmods.dev/badge/skills/2jihan/show-me-your-eta/turn-eta.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 | $0.00060 | $0.01469 |
| Opus 5.5 | $0.00024 | $0.00588 |
| Sonnet 5.5 | $0.00012 | $0.00294 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
turn-eta 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 2mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
turn-eta — say when this turn will be done, then learn from what it took
Before the work starts, write out the steps as a numbered list and say when it will be finished. Time each step as it lands. When the turn ends, close the reply with the time it actually finished. The next estimate reads that log.
When this runs
Every turn that contains real work — editing a file, running a command, searching the codebase.
- Work in the turn → call
planbefore starting and open your reply with what it prints, in the order it prints it: the**ETA …**line first, on its own, then the numbered steps. The finish time is what the reader came for; the steps below are the reasoning behind it. Callstep <id>as each step lands, anddone <id>when the turn's work is finished. - The last paragraph is a time too, and which time depends on whether anything is still running.
- Everything finished before you write the reply → the whole block
doneprints: the finish line the finish line fromdone. By then the ETA has expired; reprinting it hands the reader a guess the clock already disproved, while the per-step times show where it went wrong. - Something is still running (a background job, a delegated task) → the forecast:
**ETA 17:45**. Recompute it as you write, never paste the numberplanprinted earlier.
- Everything finished before you write the reply → the whole block
- Conversation-only turn (answering a question, deciding what to build) → do nothing. It is noise.
- A one-line fix is not worth the ceremony either. Use it when there is more than one step.
Commands
Pure Node, no install. Call it from wherever the skill is installed.
# before the work — name the steps and get an ETA
node <skill>/scripts/eta.js plan \
"reproduce the failure" "fix the date parser" "update the fixtures" "re-run the suite" \
--provider anthropic --model claude-opus-5 --size M
# **ETA 17:45** (14 min)
#
# 1. reproduce the failure
# 2. fix the date parser
# 3. update the fixtures
# 4. re-run the suite
#
# 4 steps, ~14 min (3.5 min/step from anthropic/claude-opus-5 M, 6 turns)
#
# (last 6 estimates ran 3 min long)
# turn id: 48i35qek
# each time a step lands — measured, and the rest is re-forecast from the measured pace
node <skill>/scripts/eta.js step 48i35qek
# 2/4 fix the date parser — 8m 06s
#
# **ETA 17:49** (4 min later)
# when the turn's work is done
node <skill>/scripts/eta.js done 48i35qek
# **FINISHED 17:48** (estimated 14 min / actual 17 min)
# what the log says right now
node <skill>/scripts/eta.js stats
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 118 lines · 60 tokens per session scan A 1d601d99694e
turn-eta is a skill published in the GitHub repository 2JIHAN/show-me-your-eta (1 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,469 once invoked, about $0.0002 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.