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-refresh)<a href="https://agentmods.dev/skills/coltonjosephdean-rgb/talk-to-anyone/coach-refresh"><img src="https://agentmods.dev/badge/skills/coltonjosephdean-rgb/talk-to-anyone/coach-refresh/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-refresh"><img src="https://agentmods.dev/badge/skills/coltonjosephdean-rgb/talk-to-anyone/coach-refresh.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 | $0.00019 | $0.00275 |
| Opus 5 | $0.00010 | $0.00138 |
| Sonnet 5 | $0.00004 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
coach-refresh 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.
What it actually says
/coach-refresh — rebuild a persona
The user wants $ARGUMENTS rebuilt from scratch (their content has moved on, or the
first build was thin). If $ARGUMENTS is empty, ask who to refresh.
- Resolve the personas directories the same way as /coach Step 0
(
${CLAUDE_PLUGIN_DATA}/personasprimary,~/.claude/talk-to-anyone/personaslegacy fallback) and the person's slug. - Wherever
<personas>/<slug>/exists (check both locations), delete only itspersona.md,videos.json, andtranscripts/contents — that's the entire cache for this person. - Run the full
/coachbuild for the name: read${CLAUDE_PLUGIN_ROOT}/skills/coach/SKILL.mdand follow it from Step 1 (the cache check will miss, forcing fresh research and transcript pulls). - Finish by adopting the rebuilt persona per /coach Step 6, and note in the handoff line that it was rebuilt fresh.
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 · 24 lines · 19 tokens per session scan A 8068106f4291
coach-refresh is a skill published in the GitHub repository coltonjosephdean-rgb/talk-to-anyone (60 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 275 once invoked, about $0.0001 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.