talk-roberts-ai-native-brownfield

talk-roberts-ai-native-brownfield is a skill for Codex from jscraik/Agent-Skills. It costs 125 tokens per session (1,244 once invoked), scanned A, original, Apache-2.0.

A reference guide to a talk about using AI to evolve large existing codebases. It discusses test oracles, flaky tests, refactoring, and keeping developers involved.

In plain words
What is it for?
Use it to learn about checking AI-generated changes against an external behaviour reference, removing flaky tests, and treating refactoring as routine work.
Why use it?
It addresses the difficulty of changing complex older systems when tests may be unreliable and the intended behaviour is not obvious.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to learn about checking AI-generated changes against an external behaviour reference, removing flaky tests, and treating refactoring as routine work.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-roberts-ai-native-brownfield"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-roberts-ai-native-brownfield.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,244 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 $0.00125 $0.01244
Opus 5 $0.00063 $0.00622
Sonnet 5 $0.00025 $0.00249
Haiku 4.5 $0.00013 $0.00124

Measured 8d ago against content hash b93be29e2cff, 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-ai-native-brownfield 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 8d 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-ai-native-brownfield/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stop Maintaining, Start Evolving: Applying AI-Native Practices to Brownfield Codebases — Katie Roberts

Katie Roberts shares lessons from a hands-on experiment: using AI to reverse-engineer and rebuild an S3-compatible object storage system (~350k lines of Rust, written in a few months) after MinIO stopped maintaining theirs. The talk argues that AI-assisted development of large complex systems is feasible if you stay in the loop, use an external test oracle to ground behaviour, kill flaky tests immediately, and treat refactoring (and throwing code away) as a routine part of the feedback loop — not as failure.

Supporting files

Two files accompany this skill and must be consulted before answering:

  • outline.md — contains: section headers with line-range pointers into the transcript, a terminology glossary (test oracle, human-in-the-loop, refactor weeks, type-driven authorisation, AI-built tracing, etc.), and a "Named frameworks / concepts" index.
  • transcript.md — the full talk transcript. Speaker labels are absent; the bulk is Katie Roberts presenting, with unlabelled audience questions at the end. A participants list appears in the transcript header.

Grounding rules and general workflow — MUST follow when answering

Apply these steps for every query:

  1. Read outline.md to find the relevant section(s) and any applicable glossary or framework entries.
  2. Read the corresponding range(s) of transcript.md.
  3. Answer using safe excerpts from transcript.md. Never put quotation marks around paraphrased content. Cite line numbers so the user can verify.
  4. If a claim isn't in transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge.
  5. Speaker attribution is unreliable — the source has no per-speaker labels. Prefer phrasing like "an audience member asked..." for questions, and only attribute to Katie when the content is clearly her presenting. Cross-reference any named addressee with the participants list in the transcript header / outline.md before attributing.

Read the full file on GitHub · 79 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. 8d ago First seen · 79 lines · 125 tokens per session scan A b93be29e2cff

Subscribe to this mod's changes

talk-roberts-ai-native-brownfield is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,244 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

reliability

Use when user asks to stress-test the system, validate reconnection behavior, check for race conditions, or verify end-to-end data flow integrity.

brennhill/Kaboom-Browser-AI-Devtools-MCP · 33 tokens

trace

Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…

jeremylongshore/tons-of-skills-marketplace · 84 tokens

quality-hooks

Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.

a5c-ai/babysitter · 53 tokens

moai-workflow-loop

Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.

modu-ai/moai-adk · 44 tokens

moai-workflow-testing

Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.

modu-ai/moai-adk · 47 tokens

verify

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.

oliver-kriska/claude-elixir-phoenix · 33 tokens