talk-dubnov-merge-rate-ai-adoption

talk-dubnov-merge-rate-ai-adoption is a skill for Codex from jscraik/Agent-Skills. It costs 139 tokens per session (997 once invoked), scanned A, original, Apache-2.0.

A reference guide to a talk about measuring AI adoption by tracking merge rate—the frequency with which contributors successfully get code changes into a shared codebase. It focuses on a product manager using AI to write and merge code.

In plain words
What is it for?
Use it to discuss merge-rate measurement, safe coding by non-engineers, internal tools that support them, and reducing developer involvement in routine changes.
Why use it?
It gives teams a way to measure real contributions instead of counting licences or asking whether people say they use AI.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to discuss merge-rate measurement, safe coding by non-engineers, internal tools that support them, and reducing developer involvement in routine changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption
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 jscraik/Agent-Skills --skill talk-dubnov-merge-rate-ai-adoption
Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills

Made for: 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 talk-dubnov-merge-rate-ai-adoption

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption/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 talk-dubnov-merge-rate-ai-adoption

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-dubnov-merge-rate-ai-adoption.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 997 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 $0.00139 $0.00997
Opus 5 $0.00069 $0.00498
Sonnet 5 $0.00028 $0.00199
Haiku 4.5 $0.00014 $0.00100

Measured 12d ago against content hash ef568a317cb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-dubnov-merge-rate-ai-adoption 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.

Plugins/aidevcon/skills/talk-dubnov-merge-rate-ai-adoption/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When Our PM Started Writing Code: What Merge Rate Taught Us About AI Adoption — Tammuz Dubnov

This skill grounds every response in outline.md, transcript.md, and quote.md from Tammuz Dubnov's talk.

Grounding Workflow

  1. Check quote.md for a strong pre-extracted quote on the topic.
  2. Read outline.md to find the relevant section, framework, or glossary entry.
  3. Read the matching range of transcript.md.
  4. Verify every quoted phrase appears verbatim in transcript.md before using quotation marks.
  5. If the located material only partially answers the user, say what the talk covers and what it does not cover.

Key Concepts from the Talk

Use these as anchors when routing user questions to the right section of the transcript:

  • Merge Rate — The primary metric Tammuz proposes for measuring AI adoption; tracks how frequently contributors (including non-engineers) successfully merge code.
  • Non-technical contributors shipping PRs — The talk's central case study: a PM writing and merging code with AI assistance.
  • Harness Engineering — The practice of building internal tooling and scaffolding that allows non-engineers to contribute safely.
  • Zero-dev-touch Rate — A metric tracking how often AI-generated contributions require no developer intervention before merging.
  • Calamarous Coding — A term from the talk; locate its definition and context in transcript.md before explaining it.
  • PM-to-engineer authority collapse — The talk's framing of how AI shifts decision-making and contribution authority across traditional role boundaries.
  • AI adoption ROI — Tammuz's argument for how merge rate and related metrics translate AI tooling investment into measurable organisational output.
  • AI-native org design — The broader organisational framework the talk proposes, built around these metrics and practices.

Response Formats by Request Type

Factual question about the talk

Tammuz frames the core metric as merge rate: "[safe excerpts from transcript.md]". In the talk, this matters because [one-sentence explanation grounded in the same section].

Read the full file on GitHub · 65 lines

Files

What ships with it

4 files 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 · 65 lines · 139 tokens per session scan A ef568a317cb5

Subscribe to this mod's changes

talk-dubnov-merge-rate-ai-adoption is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 139 tokens to every session and 997 once invoked, about $0.0007 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.