coach

coach is a skill for Claude Code from coltonjosephdean-rgb/talk-to-anyone. It costs 70 tokens per session (1,662 once invoked), scanned A, original, MIT.

A coaching mode that researches a public figure’s interviews, books, articles, quotes, and available video transcripts, then adopts a persona based on that material.

In plain words
What is it for?
Use it to ask a living or historical public figure for guidance, ideas, or feedback throughout a conversation.
Why use it?
It gives you advice in the style of a specific real person instead of a generic coaching voice, while grounding the conversation in their documented work.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the talk-to-anyone plugin — 5 skills shipped together

Good fit Use it to ask a living or historical public figure for guidance, ideas, or feedback throughout a conversation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add coltonjosephdean-rgb/talk-to-anyone
Claude Code
/plugin install talk-to-anyone

Made for: Claude Code.

Or install talk-to-anyone, the plugin that ships this one along with the rest of its 5 skills.

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/skills/coltonjosephdean-rgb/talk-to-anyone/coach/github.svg)](https://agentmods.dev/skills/coltonjosephdean-rgb/talk-to-anyone/coach)
Your own site
<a href="https://agentmods.dev/skills/coltonjosephdean-rgb/talk-to-anyone/coach"><img src="https://agentmods.dev/badge/skills/coltonjosephdean-rgb/talk-to-anyone/coach/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.

agentmods 80×15 button for coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/coltonjosephdean-rgb/talk-to-anyone/coach"><img src="https://agentmods.dev/badge/skills/coltonjosephdean-rgb/talk-to-anyone/coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00070 $0.01662
Opus 5 $0.00035 $0.00831
Sonnet 5 $0.00014 $0.00332
Haiku 4.5 $0.00007 $0.00166

Measured 13d ago against content hash 8b1699b5a47a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 13d 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.

skills/coach/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/coach — talk to anyone

The user wants to talk to $ARGUMENTS as their personal coach. Your job: become that person, grounded in their real public content — not a generic impression.

If $ARGUMENTS is empty, ask who they want to talk to, then continue.

Step 0 — Resolve the persona directory

Personas are cached so a person only has to be built once. Resolve DATA_DIR in this order:

  1. ${CLAUDE_PLUGIN_DATA} — if that substituted to a real absolute path, use <that path>/personas
  2. Otherwise fall back to ~/.claude/talk-to-anyone/personas

When READING (cache checks, loading a persona), check the primary location first and then ~/.claude/talk-to-anyone/personas as a legacy fallback — personas built before the plugin was installed live there. When WRITING, always use the primary location. Create the directory if it doesn't exist. Slugify the person's name (lowercase, hyphens: "Alex Hormozi" → alex-hormozi) — but FIRST correct the spelling in Step 1; the slug comes from the resolved real name, not the raw input.

Step 1 — Identify the real person

The name may be misspelled or transcribed from voice ("alex formosi" → Alex Hormozi). Web-search the name. Resolve to the most prominent public figure that matches. If two genuinely famous people share the name, ask the user which one — otherwise just proceed and state your assumption in one line ("Assuming you mean Alex Hormozi, the Acquisition.com founder").

Check the cache: if DATA_DIR/<slug>/persona.md exists, read it and skip straight to Step 5. Mention it loaded from cache in one line.

The persona is built from TWO source streams, always both: their spoken content (Steps 2-3, when any exists) and deep web research (Step 4, every build). YouTube is an add-on that sharpens the voice — it is NOT a requirement. Authors, executives, athletes, even historical figures all work. Scale effort adaptively: a video-rich creator needs ~10-12 transcripts and light web work; a no-video person needs deeper web mining. Aim for a 2-5 minute build either way; take the best sources, not all of them.

Read the full file on GitHub · 124 lines

Files

What ships with it

1 file 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.

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. 13d ago First seen · 124 lines · 70 tokens per session scan A 8b1699b5a47a

Subscribe to this mod's changes

coach is a skill published in the GitHub repository coltonjosephdean-rgb/talk-to-anyone (60 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 1,662 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 skills, from other repositories

self-improve

The deliberate self-improvement loop for the maintainer — step back from fixing issues and improve Heimdall's OWN capability. Ports karpathy/autoresearch to Heimdall's routing/planning: collect evidence from metrics.jsonl + queue dead/done stats → form testable hypotheses → run a bounded routing experiment → evaluate…

randomittin/heimdall · 0 tokens

stacks

Load stack-specific knowledge (conventions, exact lint/test/build commands, common failure patterns) onto the current role agent for the project's detected tech stack(s) — Next.js, React Native, Spring Boot, FastAPI, Django, Rust, etc. Use at the start of any task in an unfamiliar or newly-onboarded repo, or whenever…

randomittin/heimdall · 85 tokens

transmute

Comprehend an existing feature, then PORT it to another app (optionally upgrading it) or INTEGRATE/transform it in place — including swapping the vendor behind the scenes while preserving the exact UX. Use for "port/re-implement/clone this feature into ", "swap/migrate the vendor behind but keep the UX", "figure out…

Alexander-Tyagunov/magician · 94 tokens

confluence

Work with Confluence over its REST API (no MCP) — read/search (CQL), summarize pages, find docs, create/update/comment/label. Use for any read/search/create/update on Confluence pages, or references to a remembered space, page, or doc.

Alexander-Tyagunov/magician · 58 tokens

divine

Thorough, research-grounded code review of a change, PR, or MR — multi-lens (correctness, security, simplification, tests), severity-ranked with impact + fix, configurable depth, optional PR comments. Use when asked to review code, "do a code review", "review this PR/MR", "review my changes/diff/branch", or audit a…

Alexander-Tyagunov/magician · 85 tokens

conjure

Structured design dialogue with a visual companion — produces an approved spec and design artifacts before any implementation begins. Use at the start of a feature, before writing code.

Alexander-Tyagunov/magician · 36 tokens