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 instructions/fmind/dot/agents-mdgit clone --depth 1 https://github.com/fmind/dotWrote 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/instructions/fmind/dot/agents-md)<a href="https://agentmods.dev/instructions/fmind/dot/agents-md"><img src="https://agentmods.dev/badge/instructions/fmind/dot/agents-md.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 | $0.02091 | $0.02091 |
| Opus 5 | $0.01045 | $0.01045 |
| Sonnet 5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
dot AGENTS.md 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 today.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md (Project)
This is fmind/dot — a chezmoi + mise dotfiles repo for AI-CLI-first development on Linux and Mac OS with Go and Python as the core programming languages.
User-facing install and usage docs live in README.md; this file is for agents working inside the repo.
House rules
- Chezmoi: Edit the source tree (this repository), never deployed copies under
$HOME; automation always runschezmoi apply --forceso a prompt can never block. Naming, templates, and secrets: chezmoi skill. - GitHub Access: Use
ghCLI for repository, issue, and PR operations. - Git Push to Main: Direct commit/push to
mainbranch is permitted (no feature branch required). - Lint-before-done:
mise run all(format + check + test + build, the same gate CI runs) must pass before reporting a task complete. - Markdown Lists: Only use
1.for all numbered list items in markdown files to ensure correct dynamic rendering. - No-Hard-Wrap: Every
*.mdkeeps each paragraph on a single line. - No-Sudo: Stay user-space; install via
mise. - README Scope: Keep setup/auth instructions in
README.md; exclude repository tasks, aliases, and workflows. - Secrets:
*.agefiles are encrypted; never modify or commit decrypted versions. - Theme: Tokyo Night (Moon) is default across every tool that supports theming.
- Vim mode: Enable in every TUI that supports it.
Workflows
Tasks run via mise run <task>. Do not use mr — it is an interactive-only fish abbreviation.
Aliases split into two namespaces so a mistyped letter can never fire the wrong kind of task:
- Common tasks take the canonical one-letter alias from the mise skill:
aall,bbuild,ccheck,fformat,iinstall,ttest,wwatch (plusc*/f*for subtasks, e.g.cgcheck:go,fdformat:dprint). - Project management tasks take an
m-prefixed alias:maapply,mddiff,medeploy,mffull,mgcompletions,mhhooks,mklock,modoctor,mpprune,mrrelease,mttools,mtrtrust,muupgrade,mvvim,mxverify.
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.
- today First seen · 105 lines · 2,091 tokens per session scan A 75133148c4fc
dot AGENTS.md is an instructions file published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 2,091 tokens to every session, about $0.0105 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 2026-09-03.
Other instructions, from other repositories
dotfiles AGENTS.md
Instructions for sebastienrousseau/dotfiles, covering project overview, key commands, repository layout, chezmoi naming conventions and conventions.
dotfiles copilot-instructions.md
Copilot instructions for shunk031/dotfiles, a project described as: 💻 My dotfiles powered by chezmoi; built around Rust-based tools (sheldon/starship/mise, etc.) featuring a unified coding-agent setup across Codex, Claude Code, and Gemini.
dotfiles CLAUDE.md
Claude Code instructions for laurigates/dotfiles, covering claude.md, ⚠️ public repository, chezmoi quick reference, claude code directories and plugins.
dotfiles AGENTS.md
AGENTS.md instructions for shunk031/dotfiles, covering agents.md, repository context, skills, comment policy and development setup.
dotfiles AGENTS.md
Instructions for fmind/dotfiles, covering agents.md (project), house rules, conventions, workflows and agents.
dotfiles AGENTS.md
Cross-platform dotfiles managed by Chezmoi with Homebrew/apt and per-language version managers. One-command bootstrap for macOS and Linux with Neovim, Tmux, Zsh, and AI agent skills.