What is agent-project?

A guide for setting up shared project instructions and reusable skills for several coding agents. It keeps common rules in files such as AGENTS.md while storing each tool's own settings and agent files in its native location.

Use it to bootstrap agent instructions, project skills, prompt files, tool-specific settings, and MCP configuration for Codex, Claude, OpenCode, Antigravity, and Copilot.

It prevents the same project rules from being copied inconsistently across tools and reduces confusion about where configuration belongs.

agent-project — Skill by fmind

Install

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.

agentmods

npx agentmods add skills/fmind/dotfiles/agent-project

Any agent

npx skills add fmind/dotfiles --skill agent-project

Clone the repo

git clone --depth 1 https://github.com/fmind/dotfiles

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00043	$0.01061
Opus 5	$0.00022	$0.00531
Sonnet 5	$0.00009	$0.00212
Haiku 4.5	$0.00004	$0.00106

Measured yesterday against content hash 660f0103fe97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-project 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 yesterday.

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.

skills/agent-project/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set Up Agents on a Project

Create the portable instruction and skill layer once, then add only the tool-specific configuration the project needs.

Workflow

Create the Shared Layer:
```
mkdir -p .agents/skills .agents/prompts
touch AGENTS.md
```
Start AGENTS.md from the minimal project template, then put project-wide rules there, store reusable project skills in .agents/skills/<name>/SKILL.md, and keep prompt files in .agents/prompts/ (globally gitignored by default).
Add Tool-Specific Files Only When Needed:
- Antigravity: use .agents/settings.json for workspace settings and .agents/mcp_config.json for MCP. It respects .gitignore; do not invent an .antigravityignore.
- Codex: use .codex/config.toml for trusted project overrides and MCP. Codex reads AGENTS.md and .agents/skills natively.
- OpenCode: use opencode.json for settings and MCP. OpenCode reads AGENTS.md and .agents/skills natively.
- Claude: create CLAUDE.md containing @AGENTS.md, link .claude/skills to ../.agents/skills, and use .mcp.json for project MCP servers.
- Copilot: Copilot CLI reads AGENTS.md and .agents/skills natively. Use .github/copilot-instructions.md only for additional repository-wide Copilot instructions and .github/mcp.json or .mcp.json for MCP.
Inspect Before Creating Links: Never replace an existing CLAUDE.md or .claude/skills path without reviewing and preserving its content.
Keep Secrets Out: Add local credentials, generated agent state, and secret-bearing overrides to .gitignore. Commit only portable configuration.
Validate Each Installed CLI: Start each supported CLI from the repository root and confirm that instructions, skills, and explicitly configured MCP servers load.

Shared Layout

<repository-root>/
├── AGENTS.md
└── .agents/
    ├── prompts/
    └── skills/
        └── <name>/
            └── SKILL.md

Read the full file on GitHub · 91 lines

Files

What ships with it

1 file 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.

templates/AGENTS.md 1.1 KB

Changes

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.

yesterday First seen · 91 lines · 43 tokens per session scan A 660f0103fe97

Subscribe to this mod's changes

agent-project is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 1,061 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 2026-08-31.

Data and AI ai-agents chezmoi claude-code dotfiles fish-shell gemini-cli

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

vibe

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…

sebastienrousseau/dotfiles · 137 tokens

aiq-research

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

laurigates/dotfiles · 25 tokens

obsidian-bases

Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.

laurigates/dotfiles · 49 tokens

Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…

laurigates/dotfiles · 117 tokens

chezmoi-expert

Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…

laurigates/dotfiles · 88 tokens

agent-project