Modern Web Guidance is a source repository for coding-agent skills that provide web-platform guidance, recommended practices, and browser compatibility information. It helps coding agents choose newer web APIs and patterns when generating web applications. The catalogue skills are the guidance produced and maintained by this project.
Borrowing it
Nothing to install: this file belongs to GoogleChrome/modern-web-guidance-src. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GoogleChrome/modern-web-guidance-src/main/.agents/skills/project-discipline-guides/SKILL.mdgit clone --depth 1 https://github.com/GoogleChrome/modern-web-guidance-srcWrote 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/googlechrome/modern-web-guidance-src/project-discipline-guides)<a href="https://agentmods.dev/skills/googlechrome/modern-web-guidance-src/project-discipline-guides"><img src="https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/project-discipline-guides/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/googlechrome/modern-web-guidance-src/project-discipline-guides"><img src="https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/project-discipline-guides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00971 |
| Opus 5 | $0.00019 | $0.00485 |
| Sonnet 5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
project-discipline-guides 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 10d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Discipline Guides
This skill facilitates the "Differential Knowledge Refactor" of technical guides. It ensures that SKILL.md files for specific disciplines are lean, context-efficient, and strictly additive to what modern AI models already know natively.
Workflow: The Inverse Knowledge Filter
The goal is to aggressively "whittle down" a target guide (the Target) by removing any content that is natively understood by modern coding models.
1. Generate Knowledge Mirrors
Use the provided script to generate "Redundancy Mirrors"—comprehensive guides of what Gemini, Claude, and Codex consider "Common Knowledge" for a given discipline, and intersect them into a single LCD mirror.
# Ensure that model setup is configured (instructions are in the top level readme)
node .agents/skills/project-discipline-guides/scripts/generate_mirrors.ts <discipline_name>
This will create files inside the .agents/skills/project-discipline-guides/mirrors/ directory:
mirrors/<discipline>/gemini_mirror.md(via Gemini - temporary)mirrors/<discipline>/claude_mirror.md(via Claude - temporary)mirrors/<discipline>/codex_mirror.md(via Codex - temporary)mirrors/<discipline>/mirror.md(Unified Redundancy Mirror intersection)
[!IMPORTANT] Ensure that the unified Redundancy Mirror (
.agents/skills/project-discipline-guides/mirrors/<discipline>/mirror.md) has been successfully generated. This mirror represents the exact mathematical intersection of all three source models, preventing pruning errors and reducing context window overhead.
2. Perform the Inverse Filter (Agent Task)
As the agent, read the Target guide and the unified Redundancy Mirror (.agents/skills/project-discipline-guides/mirrors/<discipline>/mirror.md).
- Strict A - B Comparison: Compare rules in the Target guide strictly against the unified Redundancy Mirror. You should ONLY remove a rule or pattern from the Target guide if it is fully and clearly covered in the Redundancy Mirror.
- No Subjective Self-Attestation: Rely exclusively on the literal content present in the Redundancy Mirror. Do not prune rules based on your own subjective self-attestation of what you "know" or would do by default. If a concept is not in the Redundancy Mirror, it remains in the Target guide.
- Avoid Blind Bullet-Point Deletions: If a single bullet point or rule in the Target contains multiple guidelines or APIs, do not delete the entire bullet point just because some parts of it are common knowledge. Carefully split or dissect the rule, pruning only the redundant parts and explicitly retaining any differential knowledge.
- Preserve Differential Knowledge: Keep only what is unique to this project or necessary to guide the AI effectively. This generally includes:
- Rules that counter common AI biases.
- Conventions chosen among valid alternatives.
- Advanced performance patterns, security constraints, or heuristics that models know but often omit in default outputs.
What ships with it
7 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.
- 10d ago First seen · 60 lines · 39 tokens per session scan A 27802bc226b6
project-discipline-guides is a skill published in the GitHub repository GoogleChrome/modern-web-guidance-src (1,022 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 971 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…