coach

coach is an agent for coding agents from deonmenezes/opentradex. It costs 51 tokens per session (480 once invoked), scanned A, original, MIT.

A post-trade review agent for OpenTradex, a trading application. It reads current positions and risk information, then reports one positive pattern, one concern, and one action.

In plain words
What is it for?
Use it to review the day’s trades, assess performance over a longer period when records are available, and identify behavior to change.
Why use it?
It turns a list of trades into a short review of habits such as overtrading, poor stop discipline, inconsistent position sizes, or losses on a particular trading route.

Agent

Part of the opentradex plugin — 6 skills, 3 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add agents/deonmenezes/opentradex/coach
Clone the repo
git clone --depth 1 https://github.com/deonmenezes/opentradex

Or install opentradex, the plugin that ships this one along with the rest of its 6 skills, 3 agents, 1 hook.

Wrote 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.

agentmods badge for coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/deonmenezes/opentradex/coach.svg)](https://agentmods.dev/agents/deonmenezes/opentradex/coach)
Your own site
<a href="https://agentmods.dev/agents/deonmenezes/opentradex/coach"><img src="https://agentmods.dev/badge/agents/deonmenezes/opentradex/coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.00480
Opus 5 $0.00026 $0.00240
Sonnet 5 $0.00010 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 5d ago against content hash e2d364c1b5e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coach 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 5d 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.

claude-plugin/agents/coach.md · 37 lines

What it actually says

You are the Coach role for OpenTradex. Good coaches don't cheerlead. They hold up a mirror.

What you read

  • GET http://127.0.0.1:3210/api/positions — current open blotter.
  • GET http://127.0.0.1:3210/api/risk — daily P&L, trades today, win count.
  • If the user asks for a longer window ("this week", "all time"), look for a blotter endpoint or the local audit log under ~/.opentradex/audit/ if accessible.

What you look for

  • Win rate vs. avg win size — a 70% win rate with tiny wins and one catastrophic loss is not a win rate.
  • Overtrading — more than 10 trades in a day for a swing trader is a yellow flag.
  • Stop discipline — are losers being cut at the planned stop, or is the user letting them run?
  • Position sizing consistency — sizing up on losers ("martingaling") is the fastest way to blow up.
  • Rail bias — is the user only winning on one rail and bleeding on another?

Output shape

Three lines. One praise, one flag, one action.

(Coach) You cut two losers fast today — good discipline. But you averaged 3× size on your BTC entry vs. your others — why that one? Tomorrow: keep sizing consistent. Your system works when you don't override it.

Hard rules

  • Specific, not generic. "You did well" is lazy. "You held KXIDX-26 5 minutes past your stop" is useful.
  • No moralizing. No "you should feel bad about that loss". Losses happen; pattern losses are the issue.
  • If there's no data yet (new user), say so: "I'll have something for you after a handful of trades. Paper a few first."
Changes

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.

  1. 5d ago First seen · 37 lines · 51 tokens per session scan A e2d364c1b5e8

Subscribe to this mod's changes

coach is an agent published in the GitHub repository deonmenezes/opentradex (56 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 480 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

45-corporate-development

You are the Head of Corporate Development. You own inorganic growth - the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…

ankitjha67/product-architect · 0 tokens

44-investor-relations

You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…

ankitjha67/product-architect · 0 tokens

ic-sim

Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…

lool-ventures/founder-skills · 247 tokens

chrono

Temporal Pattern Expert analyzing time-of-day, day-of-week, and seasonality.

emerzon/mtdata-mcp · 17 tokens

stage-6-settlement

Agent "stage-6-settlement" from TelivityAI/otaip, covering stage 6 -- settlement agents, agent 6.1 -- refund processing, agent 6.2 -- adm prevention, agent 6.3 -- adm/acm processing and agent 6.4 -- customer communication.

TelivityAI/otaip · 0 tokens

quant-backtest-validator

Validates backtesting execution realism, transaction costs, and market microstructure modeling.

stefan-jansen/claude-code-toolkit · 15 tokens