talk-roberts-brownfield-ai-native

talk-roberts-brownfield-ai-native is a skill for Codex from jscraik/Agent-Skills. It costs 161 tokens per session (2,012 once invoked), scanned A, original, Apache-2.0.

A reference guide to a talk about using AI to change older, already-used codebases. It explains three approaches: rebuilding a contained part, gradually replacing an old system, and changing internal structure without changing its interface.

In plain words
What is it for?
Use it to plan AI-assisted legacy-system changes, choose an evolution approach, work in small scopes, version changes, and build a reusable skills library.
Why use it?
It addresses why techniques that work for new projects do not automatically work for existing business software.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to plan AI-assisted legacy-system changes, choose an evolution approach, work in small scopes, version changes, and build a reusable skills library.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/talk-roberts-brownfield-ai-native
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-roberts-brownfield-ai-native
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-roberts-brownfield-ai-native

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-roberts-brownfield-ai-native"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-roberts-brownfield-ai-native.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,012 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 $0.00161 $0.02012
Opus 5 $0.00081 $0.01006
Sonnet 5 $0.00032 $0.00402
Haiku 4.5 $0.00016 $0.00201

Measured 9d ago against content hash b2ad67d65ede, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-roberts-brownfield-ai-native 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.

Plugins/aidevcon/skills/talk-roberts-brownfield-ai-native/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stop Maintaining, Start Evolving: Applying AI-Native Engineering in Brownfield Codebases — Katie Roberts (Nearform)

Katie Roberts (Technical Director, Nearform) argues that AI-native engineering's much-celebrated greenfield wins don't translate automatically to the brownfield codebases that make up 60–70% of enterprise software. She presents three methodologies for evolving legacy systems with AI (pseudo-greenfield development, strangler fig pattern, branch by abstraction) and a set of core principles — start with developers as eyewitnesses, plan extensively, work in small scopes, version everything, build a skills library — illustrated with two Nearform case studies (a "six months in eight weeks" pseudo-greenfield rebuild and a 500k-line AG Grid upgrade via branch by abstraction).

Grounding rules — MUST follow when answering

  1. Before answering any specific question, read outline.md to locate the relevant section, then read that section of transcript.md.
  2. When attributing words, quote short, non-sensitive excerpts from transcript.md. Never put quotation marks around paraphrased content.
  3. If a claim isn't in transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge.
  4. Cite by transcript line range or timestamp whenever possible.
  5. Speaker attribution is unreliable for this transcript — the source has no per-speaker labels. Prefer phrasing like "Katie said..." (she is the sole presenter for most of the transcript) but for the intro and Q&A use hedged phrasing like "the host/MC introduced..." or "an audience member asked..." unless a sentence clearly names a specific speaker. Do not invent attributions.
  6. Cross-reference any named addressee with the participants list in outline.md before attributing. Note that several names in the transcript are speech-to-text artifacts (e.g. "Alan Hills" likely refers to Adam Tornhill's Your Code as a Crime Scene; "Hannah foxton" is a referenced prior speaker; "Don" refers to a previous-talk speaker). Preserve these as-is when quoting.

Read the full file on GitHub · 92 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. 9d ago First seen · 92 lines · 161 tokens per session scan A b2ad67d65ede

Subscribe to this mod's changes

talk-roberts-brownfield-ai-native is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 161 tokens to every session and 2,012 once invoked, about $0.0008 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.