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 jscraik/Agent-Skills --skill talk-podjarny-skills-are-the-new-codegit clone --depth 1 https://github.com/jscraik/Agent-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/jscraik/agent-skills/talk-podjarny-skills-are-the-new-code)<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.
<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>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 | $0.00104 | $0.00961 |
| Opus 5 | $0.00052 | $0.00481 |
| Sonnet 5 | $0.00021 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
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.
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 relevanttranscript.mdsection.- 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
- Read
outline.mdto locate the relevant section. - Check
quote.mdfor candidate safe excerpts from that section. - Read the corresponding
transcript.mdlines before using a claim or excerpt.quote.mdis a navigation aid, not standalone evidence. - Anchor every key claim in a safe excerpt from
transcript.md; cite the line range and separate the excerpt from any paraphrase or interpretation. - For a full-talk synthesis, identify the thesis and each relevant framework
from
outline.md, then ground each synthesis point in transcript evidence. - 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, orunknown. - Keep talk evidence separate from repository evidence. A transcript explains the framework; only local artifacts and command results establish project behavior.
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.
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 · 88 lines · 104 tokens per session scan A ade98c1e1a7f
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.
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.
api-testing
REST/GraphQL API testing with automated validation — test endpoints, validate responses, check status codes, and ensure API contracts.
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"…
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.
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.
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.