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 agentmods add skills/eficode/modern-ai-developer-stack/setup-cascading-contextnpx skills add eficode/modern-ai-developer-stack --skill setup-cascading-contextgit clone --depth 1 https://github.com/eficode/modern-ai-developer-stackWhat 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 | $0.00000 | $0.02275 |
| Opus 5 | $0.00000 | $0.01137 |
| Sonnet 5 | $0.00000 | $0.00455 |
| Haiku 4.5 | $0.00000 | $0.00228 |
Grade A, and why
setup-cascading-context 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 2d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Setup Cascading Context
Description
This skill audits a project's existing context files, validates consistency across cascading context layers, and generates missing context files based on the cascading context methodology.
Use this skill when:
- Setting up cascading context for a new project
- Auditing an existing project's context structure
- Migrating from tool-specific to tool-agnostic context
Prerequisites
- Basic understanding of cascading context (see
docs/guides/cascading-context.md) - Git repository with at least one code file
Inputs
- Project path (required): Path to the project directory to audit
- Mode (optional):
audit(default) orgenerateaudit: Check existing context and report issuesgenerate: Create missing context files with templates
Outputs
Audit Mode
A report containing:
- Discovered context files at each level
- Missing context files
- Duplicated guidelines across layers
- Tool-specific files that should reference tool-agnostic context
- Recommendations for improvement
Generate Mode
Creates missing context files:
AGENTS.md(if missing at repository root)docs/standards/[language].md(for detected languages)collections/[stack].md(optional, based on detected stack)- Project
README.md(if missing or minimal) - Module-level READMEs (for large subsystems, optional)
Instructions
Step 1: Discover Project Structure
- Navigate to the project directory specified by the user
- Identify the repository root (look for
.gitdirectory) - Detect programming languages used (check file extensions:
.ts,.js,.py,.rs, etc.) - Detect frameworks (check
package.json,requirements.txt,Cargo.tomlfor dependencies) - Identify project type (web service, CLI tool, library, etc.)
Step 2: Discover Existing Context Files
Search for context files at each level:
-
Repository Level:
AGENTS.mdREADME.mdCONTRIBUTING.md
-
Standards Level:
docs/standards/*.md- Common patterns:
typescript.md,python.md,rust.md, etc.
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.
- 2d ago First seen · 266 lines · 0 tokens per session scan A 3219bbcaeeb7
setup-cascading-context is a skill published in the GitHub repository eficode/modern-ai-developer-stack (11 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,275 tokens. 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…