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.
npx skills add x3allamerican/skills --skill driver-coaching-conversationsgit clone --depth 1 https://github.com/x3allamerican/skillsWrote 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/x3allamerican/skills/driver-coaching-conversations)<a href="https://agentmods.dev/skills/x3allamerican/skills/driver-coaching-conversations"><img src="https://agentmods.dev/badge/skills/x3allamerican/skills/driver-coaching-conversations/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/x3allamerican/skills/driver-coaching-conversations"><img src="https://agentmods.dev/badge/skills/x3allamerican/skills/driver-coaching-conversations.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 | $0.00078 | $0.01942 |
| Opus 5 | $0.00039 | $0.00971 |
| Sonnet 5 | $0.00016 | $0.00388 |
| Haiku 4.5 | $0.00008 | $0.00194 |
Grade A, and why
driver-coaching-conversations 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 9d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driver Coaching Conversations
A coaching conversation is the highest-leverage 10 minutes in fleet safety culture. Done well, it changes behavior and strengthens the driver-employer relationship. Done badly, it accelerates turnover.
Conversation purpose: behavior change, not punishment
Coaching is not the same as discipline. Coaching:
- Surfaces a specific behavior
- Asks the driver's perspective
- Agrees on next-step behavior
- Documents the conversation
- Schedules follow-up
Discipline (verbal warning, written warning, suspension, termination) is a separate progressive process documented in HR.
The 4-step coaching framework
Step 1 — Open with context (30 seconds)
"Hey John, thanks for stopping in. I wanted to talk about the dashcam alert from Tuesday's run on I-40. Have you got 10 minutes?"
Why: signals this is a coaching conversation, not surprise discipline. Driver isn't blindsided.
Step 2 — Show the data, not the conclusion (1 minute)
Play the video / show the event. Don't editorialize.
"This is the moment — looks like it caught a quick lane change around 14:32."
Why: data anchors the conversation. Driver can't argue with the recording.
Step 3 — Ask the driver's perspective (3 minutes)
"What was happening at that moment? Walk me through it."
Listen. Most drivers have legitimate context (a car cut them off, debris in the road, fatigue, weather). Some don't.
Follow-up questions:
- "What would you do differently next time?"
- "Is there something we could do to make this easier for you?"
- "Is anything else going on I should know about?"
Why: drivers who feel heard accept coaching. Drivers who feel attacked dig in. Also, you might learn the dashcam mis-classified an event (you can clear it).
Step 4 — Agree on next step + document (2 minutes)
If the behavior is real: "OK, so the plan is — next time you feel that tight on a lane change, you'll back off and find a longer gap. Sound right? I'll note this in your file as a coaching conversation. No write-up. Let's revisit at the end of the month."
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.
- 9d ago First seen · 199 lines · 78 tokens per session scan A 75902ce692ab
driver-coaching-conversations is a skill published in the GitHub repository x3allamerican/skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,942 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 2026-09-03.
Other skills, from other repositories
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
slack-messaging
Use when writing, drafting, scheduling, or improving a Slack message, announcement, or reply sent via the Slack MCP tools (slacksendmessage, slacksendmessagedraft, slackschedulemessage). Covers Slack markdown formatting, message structure, thread etiquette, reactions, and scheduling, and points to the right dialect…
next-action
Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
lov-canonical-store
A central file and command-line workflow for maintaining one deduplicated vocabulary list as the source for other apps.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.