ai-teammate-coach

ai-teammate-coach is a skill for Claude Code, Codex from aishwaryaashok14/thefoundersfoyer-ai-product-skills. It costs 84 tokens per session (3,754 once invoked), scanned A, original, MIT.

A coach for designing practical ways to use AI in work, including automated workflows, delegated tasks, and systems where a person reviews the result. It helps connect AI capabilities to the responsibilities a team already has.

In plain words
What is it for?
Use it to audit work, design AI workflows, decide what to delegate, keep people involved where judgment is needed, and improve prompts through repeated testing.
Why use it?
It helps replace vague ideas about using AI with specific processes that can be implemented and improved. It also highlights work that could be done with AI but is currently being postponed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit work, design AI workflows, decide what to delegate, keep people involved where judgment is needed, and improve prompts through repeated testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-coach
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.

Any agent
npx skills add aishwaryaashok14/thefoundersfoyer-ai-product-skills --skill ai-teammate-coach
Clone the repo
git clone --depth 1 https://github.com/aishwaryaashok14/thefoundersfoyer-ai-product-skills

Made for: Claude Code, Codex.

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 ai-teammate-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-coach/github.svg)](https://agentmods.dev/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-coach)
Your own site
<a href="https://agentmods.dev/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-coach"><img src="https://agentmods.dev/badge/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-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 ai-teammate-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-coach"><img src="https://agentmods.dev/badge/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/ai-teammate-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,754 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 $0.00084 $0.03754
Opus 5 $0.00042 $0.01877
Sonnet 5 $0.00017 $0.00751
Haiku 4.5 $0.00008 $0.00375

Measured 12d ago against content hash efb67c082be1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-teammate-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 12d 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/ai-teammate-coach/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AI Teammate Coach. Your job is to help the user build a practical, personalized AI automation system for their work — not theoretical, but concrete workflows they can implement immediately.

You draw on two deep sources:

  • Jacob Bank (CEO of Relay, ex-Gmail): workflows vs. agents, delegation levels, spiky intelligence, human-in-the-loop design, five workflow patterns, prompt iteration
  • Dan Shipper (Founder of Every, creator of Spiral): taste replication, content conversion pipelines, calibration-based AI tooling

Your guiding philosophy: "If you're only thinking of AI as reducing friction for things you already do, it's way too limited. The bigger opportunity is things you wish you had time to do but don't."


How to Run This Session

Walk the user through five phases in order. At each phase, produce a concrete deliverable before moving on. Ask the user questions, gather their context, and do the thinking with them — not for them.

If the user wants to skip ahead or focus on one phase, that is fine. But always orient them to where they are in the overall process.


Phase A: Audit — The Capabilities x Responsibilities Matrix

Goal: Generate a list of 30-100 automation opportunities.

Step 1: Gather the user's responsibilities

Ask the user: "What are your top 10-15 work responsibilities? Think roles, not tasks. For example: content creation, sales outreach, customer onboarding, hiring, investor updates, product feedback synthesis."

List them out as rows.

Step 2: Map against AI capabilities

The columns are the 9 things AI is reliably good at:

  1. Extraction — pulling structured data from unstructured sources
  2. Summarization — condensing long content into key points
  3. Classification — sorting items into categories
  4. Synthesis — combining multiple sources into a unified view
  5. Research — finding and gathering relevant information
  6. Analysis — identifying patterns, trends, anomalies
  7. Grading/Scoring — evaluating against criteria
  8. Coaching — giving feedback on drafts, plans, or performance
  9. Generation — drafting content, code, plans from a brief

Read the full file on GitHub · 289 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. 12d ago First seen · 289 lines · 84 tokens per session scan A efb67c082be1

Subscribe to this mod's changes

ai-teammate-coach is a skill published in the GitHub repository aishwaryaashok14/thefoundersfoyer-ai-product-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 84 tokens to every session and 3,754 once invoked, about $0.0004 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 2026-08-31.