talk-podjarny-skills-are-the-new-code

talk-podjarny-skills-are-the-new-code is a skill for Codex from jscraik/Agent-Skills. It costs 104 tokens per session (961 once invoked), scanned A, original, Apache-2.0.

A reference guide to a talk arguing that reusable instructions for coding agents should be engineered like software. It covers checks, evaluations, security testing, dependency management, and monitoring.

In plain words
What is it for?
Use it to plan quality checks, evaluation scenarios, security reviews, dependency tracking, and monitoring for agent skills.
Why use it?
It helps teams find and control failures in agent skills instead of trusting them without systematic checks.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to plan quality checks, evaluation scenarios, security reviews, dependency tracking, and monitoring for agent skills.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code
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-podjarny-skills-are-the-new-code
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-podjarny-skills-are-the-new-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code/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-podjarny-skills-are-the-new-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 961 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 $0.00104 $0.00961
Opus 5 $0.00052 $0.00481
Sonnet 5 $0.00021 $0.00192
Haiku 4.5 $0.00010 $0.00096

Measured 9d ago against content hash ade98c1e1a7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-podjarny-skills-are-the-new-code 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-podjarny-skills-are-the-new-code/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills are the new Code — Guy Podjarny

Guy Podjarny (founder of Tessl, previously founder of Snyk) argues that skills are the new unit of software being authored in the agentic-development stack, and that they deserve the same engineering rigour — static analysis, evals, security testing, dependency management, and observability — applied to code.

When To Use

Use this skill for transcript-grounded questions about the talk or for applying one of its frameworks to a user-provided project, artifact, or workflow. Do not use it as generic advice about skills when the talk does not cover the claim.

Inputs

  • The user's question or requested framework.
  • outline.md, quote.md, and the relevant transcript.md section.
  • For an application or audit, the separately authorized local truth surface.

Outputs

Return a transcript-grounded answer with safe excerpts, line ranges, and a clearly labelled paraphrase. For an application or audit, add a crosswalk that keeps the talk evidence separate from the project evidence:

Talk discipline Local evidence Status
Evals <artifact, command, or none found> present / gap / unknown

Workflow

  1. Read outline.md to locate the relevant section.
  2. Check quote.md for candidate safe excerpts from that section.
  3. Read the corresponding transcript.md lines before using a claim or excerpt. quote.md is a navigation aid, not standalone evidence.
  4. Anchor every key claim in a safe excerpt from transcript.md; cite the line range and separate the excerpt from any paraphrase or interpretation.
  5. For a full-talk synthesis, identify the thesis and each relevant framework from outline.md, then ground each synthesis point in transcript evidence.
  6. For an application or audit, inspect only the user-provided or separately authorized local truth surface, populate the crosswalk, and classify each row as present, gap, or unknown.
  7. Keep talk evidence separate from repository evidence. A transcript explains the framework; only local artifacts and command results establish project behavior.

Read the full file on GitHub · 88 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 · 88 lines · 104 tokens per session scan A ade98c1e1a7f

Subscribe to this mod's changes

talk-podjarny-skills-are-the-new-code is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 104 tokens to every session and 961 once invoked, about $0.0005 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

browser-automation

Local Python-based browser automation toolkit using Playwright. Provides command-line tools for navigating, interacting with, and testing web applications without using MCP protocols. Supports clicking, typing, hovering, screenshots, content extraction, and JavaScript execution.

archubbuck/workspace-architect · 50 tokens

api-testing

REST/GraphQL API testing with automated validation — test endpoints, validate responses, check status codes, and ensure API contracts.

kevinnft/ai-agent-skills · 27 tokens

kaboom

Use when user asks to check browser state, debug page errors, inspect network traffic, take screenshots, automate clicks or form fills, run accessibility or security audits, measure performance, generate tests, or record browser sessions. Trigger phrases: "check my browser", "debug this page", "take a screenshot"…

brennhill/Kaboom-Browser-AI-Devtools-MCP · 99 tokens

qa-check

A pre-completion quality check for a software task. It finds which files changed and runs the relevant project checks through Make, such as linting, type checks, tests, or static analysis.

Xakki/ai-agents-skills · 66 tokens

regression-test

Use when user has fixed a bug and needs a test that proves it stays fixed, or when a failure needs to be captured as a reproducible test case.

brennhill/Kaboom-Browser-AI-Devtools-MCP · 36 tokens

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