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/randynorthrup/high-quality-projects-skill/project_setupnpx skills add RandyNorthrup/high-quality-projects-skill --skill project_setupgit clone --depth 1 https://github.com/RandyNorthrup/high-quality-projects-skillWrote 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/randynorthrup/high-quality-projects-skill/project_setup)<a href="https://agentmods.dev/skills/randynorthrup/high-quality-projects-skill/project_setup"><img src="https://agentmods.dev/badge/skills/randynorthrup/high-quality-projects-skill/project_setup.svg" alt="Measured on agentmods" 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 | $0.00184 | $0.05466 |
| Opus 5 | $0.00092 | $0.02733 |
| Sonnet 5 | $0.00037 | $0.01093 |
| Haiku 4.5 | $0.00018 | $0.00547 |
Grade A, and why
project_setup 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 4d 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 — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project setup — discovery before commit one
Scaffold a new project with a confirmed product contract and the strictest practical standards for its stack. The argument is the initial project description. Use it to seed discovery; even a detailed description does not silently waive the Grill Me readiness gate.
Communication style
Status updates to the user: short, direct, no filler. Caveman style if the caveman plugin is active.
Never compress: code comments, documentation, PLAN.md rationale,
architectural reasoning, security notes, or commit messages. Brevity applies to
chat only. A terse status line and a thorough PLAN.md are not in tension.
Locating this package
Paths below use ${SKILL_ROOT}/... as a placeholder for this package's root,
including its scripts/, templates/, and skill resources. Resolve it once
with the active shell. On Windows PowerShell:
$SkillRoot = & 'C:\path\to\high-quality-projects-skill\scripts\skill-root.ps1'
On Linux, macOS, or another POSIX environment:
SKILL_ROOT="$(bash /path/to/high-quality-projects-skill/scripts/skill-root.sh)"
Both root scripts locate themselves, so they work from a plain clone, a vendored
copy, or a submodule with no environment set. They honour SKILL_ROOT, then
CLAUDE_PLUGIN_ROOT under Claude Code. Do not invoke Windows bash.exe: it can
exist as a WSL relay even when /bin/bash does not.
Nothing here is specific to one vendor. If your agent cannot run shell commands, read the files directly out of the repository — the templates are plain config files and the phases below are plain instructions.
Rule zero: scan, reuse, then create
Run this before anything else, even when the directory looks empty:
$Scan = & "$SkillRoot\scripts\detect-stack.ps1" . | ConvertFrom-Json
Or from a POSIX shell:
"${SKILL_ROOT}/scripts/detect-stack.sh" .
It returns JSON: languages present, config files that already exist, tools installed on this machine. Supplement it with a read-only search for existing code, components, types, schemas, tests, documentation, design-system files, brand assets, infrastructure, and generated-code boundaries. Then:
What ships with it
2 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.
- 4d ago First seen · 499 lines · 184 tokens per session scan A 01d182dae8f1
project_setup is a skill published in the GitHub repository RandyNorthrup/high-quality-projects-skill (1 stars, last pushed 11d ago), licensed MIT. It adds 184 tokens to every session and 5,466 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
generating-code-standards
Use when initializing a new project, onboarding a repo without a CLAUDE.md, or when the user asks to generate, create, or set up engineering standards. Triggers on "generate standards", "create CLAUDE.md", "set up project rules", "initialize project standards", "add engineering standards".
fable-discipline
Engineering discipline distilled from a forensic read of one model's work. Use when building a feature, fixing a bug, writing tests, hardening a data path, or running any task that spans multiple files, sources, or sessions. Two layers: how to RUN the task (stage it, verify each stage with a check that can fail, write…
open-draft-pr
Prepare local changes for review with an intentional commit, push, and ready PR for fallow. Use when the user wants to publish work, open a PR, or turn local changes into a reviewable branch.
address-pr-comments
Triage and address GitHub PR review feedback for fallow, then implement the agreed fixes. Use when the user wants to inspect PR comments, requested changes, or unresolved review threads and act on them.
coverage-loop
Iteratively improve Fallow Rust test coverage with cargo-llvm-cov, prioritizing meaningful untested behavior and preserving runtime correctness.