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/markshust/hcf/project-setupnpx skills add markshust/hcf --skill project-setupgit clone --depth 1 https://github.com/markshust/hcfWhat 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 | $0.00033 | $0.02844 |
| Opus 5 | $0.00016 | $0.01422 |
| Sonnet 5 | $0.00007 | $0.00569 |
| Haiku 4.5 | $0.00003 | $0.00284 |
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 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One-time interactive setup to configure a project for autonomous development.
Purpose
Create CLAUDE.md and all project configuration files in .claude/ through an interactive process with auto-detection.
Execution Steps
Step 1: Check for Existing Configuration
First, check if configuration already exists:
ls CLAUDE.md .claude/testing.md .claude/code-standards.md .claude/architecture.md 2>/dev/null
If CLAUDE.md and all 3 config files (testing.md, code-standards.md, architecture.md) exist, inform the user:
Project already configured. CLAUDE.md and config files exist in
.claude/. To reconfigure, delete CLAUDE.md and.claude/then run/project-setupagain.
Otherwise, continue with setup.
Step 2: Auto-Detect Project Type
Scan the project root for configuration files to detect the tech stack:
Check for these files (in parallel):
composer.json→ PHP/Laravel/Symfonypackage.json→ Node.js/React/Vue/Next.jsCargo.toml→ Rustgo.mod→ Gopyproject.tomlorrequirements.txt→ PythonGemfile→ Ruby/Railspom.xmlorbuild.gradle→ Java*.csprojor*.sln→ .NET
For each detected file, extract:
- Framework and version
- Testing framework (from devDependencies or test config)
- Linting/formatting tools
Example auto-detection output:
Detected project configuration:
- Framework: Laravel 11 (from composer.json)
- PHP Version: 8.3
- Testing: Pest PHP (from composer.json require-dev)
- Linting: Laravel Pint (from composer.json require-dev)
Step 3: Confirm Detection
Ask user to confirm detected configuration:
I detected the following. Is this correct? (y/n) [Show detected config]
If incorrect, ask clarifying questions about each incorrect item.
Step 4: Gather Additional Information
Ask these questions (skip if already detected):
Q1: Test Command
What command runs your tests? Detected:
./vendor/bin/pest[Enter to confirm or type custom]
Q1b: Parallel Test Command
Does your test runner support parallel execution? If so, what's the command? (e.g.,
./vendor/bin/pest --parallel,npm test -- --parallel,pytest -n auto,go test ./... -parallel 4) [Enter detected parallel command, type custom, or 'none' if not supported]
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 · 356 lines · 33 tokens per session scan A 3ae5c478315d
project-setup is a skill published in the GitHub repository markshust/hcf (67 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 2,844 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
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
engineering-workflow
可靠工程工作流的执行细则——探索→计划→TDD→系统化调试→代码审查→完成前验证。供方法论教练在开发任务中逐步引导。.
implement
Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD red-green, reviewing each via an isolated sub-agent, and persisting progress to a state file so work survives session restarts. Use when the user has a tech design (doc or settled conversation) and says…
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
write-eval
Write a live eval for new or changed runner/agent behavior using red/green TDD plus a falsification check that proves the eval fails when the behavior is broken. Use whenever you add or modify behavior that should be covered by an eval, when asked to "write an eval", "add an eval", "cover this with an eval", or after…
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.