velkross
AGENTS.md1 starsChanged 5 months agoMITView on GitHub
Guidance for AI coding agents working in this repository. Velkross is an agent harness plugin that packages Trust-Preserving Software Evolution guidance, hooks, and reusable skills for AI coding agents. The project is intended to support harnesses such as Codex, Claude Code, and Cursor while keeping the shared engineering behavior consistent across adapters. Use Vite+ (vp) as the project toolchain entry point. Vite+ manages the Node.js runtime, package manager, formatting, linting, type checks, tests, builds, and workspace tasks. It is distinct…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository9 other files it gives its agents.
- agent-memorySkill
- agent-skill-designSkill
- alignment-interviewSkill
- complexity-reviewSkill
- design-deep-modulesSkill
- project-development-docsSkill
- right-size-engineeringSkill
- tddSkill
- to-ticketsSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Use Vite+ (vp) as the project toolchain entry point.
- Very specific: line 13
After installing dependencies, read the local Vite+ documentation under node_modules/vite-plus/docs/ when tool behavior or configuration …
- Distinctive: line 23
Keep commit messages concise and searchable.
- Distinctive: line 29
Keep issues and pull requests concise and searchable.
- Distinctive: line 31
Add issue references, screenshots, test notes, and breaking-change notes only when relevant.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repository Instructions
Guidance for AI coding agents working in this repository.
Project Overview
Velkross is an agent harness plugin that packages Trust-Preserving Software Evolution guidance, hooks, and reusable skills for AI coding agents. The project is intended to support harnesses such as Codex, Claude Code, and Cursor while keeping the shared engineering behavior consistent across adapters.
Commands
Use Vite+ (vp) as the project toolchain entry point. Vite+ manages the Node.js runtime, package manager, formatting, linting, type checks, tests, builds, and workspace tasks. It is distinct from Vite.
After installing dependencies, read the local Vite+ documentation under node_modules/vite-plus/docs/ when tool behavior or configuration details matter. Start with node_modules/vite-plus/docs/guide/index.md, then open the relevant guide.
vp install: Install dependencies.vp check: Run formatting, linting, and type checks. Use--fixto apply automatic fixes.vp run test: Run tests.vp env doctor: Check setup, runtime, or package-manager behavior when something looks wrong.
Git
- Format commit messages as Conventional Commits:
<type>(<scope>): <summary>. - Keep commit messages concise and searchable.
- Include the reason for a change in the commit body when useful.
Issues and Pull Requests
- Format PR titles like commit messages so they are suitable for final squash commit titles.
- Keep issues and pull requests concise and searchable.
- Briefly summarize the main changes in PR descriptions and include the reason when useful.
- Add issue references, screenshots, test notes, and breaking-change notes only when relevant.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.