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.
/plugin marketplace add coltonjosephdean-rgb/talk-to-anyone/plugin install talk-to-anyoneWrote 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/coltonjosephdean-rgb/talk-to-anyone/coach)<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.
<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>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 | $0.00070 | $0.01662 |
| Opus 5 | $0.00035 | $0.00831 |
| Sonnet 5 | $0.00014 | $0.00332 |
| Haiku 4.5 | $0.00007 | $0.00166 |
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.
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:
${CLAUDE_PLUGIN_DATA}— if that substituted to a real absolute path, use<that path>/personas- 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.
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.
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.
- 13d ago First seen · 124 lines · 70 tokens per session scan A 8b1699b5a47a
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.
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…
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…
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…
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.
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…
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.