What is dotfiles AGENTS.md?

Repository instructions for personal configuration files, including settings for the Pi coding assistant, Neovim, Fish, and Claude.

Use them when changing Pi or Claude instructions, shell or editor configuration, symlinks, extensions, formatting rules, or related tests.

They explain where configuration lives and how Makefile-managed links are installed, preventing edits in the wrong location or conflicting assistant settings.

dotfiles AGENTS.md — Instructions file by jackfranklin

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 instructions/jackfranklin/dotfiles/agents-md

Clone the repo

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

Made for: Codex, OpenCode.

Per session 1,323 This file is loaded in full into every session.

When invoked 1,323 The same file — it is already loaded in full.

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	$0.01323	$0.01323
Opus 5	$0.00661	$0.00661
Sonnet 5	$0.00265	$0.00265
Haiku 4.5	$0.00132	$0.00132

Measured 2d ago against content hash 639f43c0aaa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotfiles 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 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.

AGENTS.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dotfiles Pi configuration

This repository contains Jack's personal dotfiles and uses explicit Makefile-managed symlinks rather than Stow. Its Pi configuration lives under pi/. Run make pi to symlink settings.json, permissions.json, and extensions/ into ~/.pi/agent/; do not edit those symlinked copies directly.

Pi reads this top-level AGENTS.md when it starts in this repository. It also searches the current directory and its parents for AGENTS.md or CLAUDE.md; this file is repository-specific and is deliberately not installed as global Pi context.

Repository conventions

Neovim configuration is in nvim/; run make lua_specs for its Lua tests.
Fish functions are in fish/functions/.
Claude's global configuration and skills are in claude/; make claude installs their symlinks. Keep every custom skill in claude/skills/; Pi discovers this directory through ~/.claude/skills. Do not create or edit standalone skills in ~/.pi/agent/skills/, as duplicate skill names collide.
Format JavaScript/TypeScript with the repository Prettier configuration: semicolons, trailing commas, and single quotes.

Pi configuration

settings.json selects the light theme, OpenAI Codex as the default provider/model, high thinking, enabled models, and discovers skills from ~/.claude/skills.
permissions.json is used by the permissions extension. It contains glob rules that classify commands and file operations as safe, approval-required, or blocked.
extensions/ is symlinked to ~/.pi/agent/extensions/. Pi auto-discovers a top-level .ts extension or a nested index.ts in that directory.
make pi_deps installs the production dependencies needed by extensions/web-fetch.
make pi_specs runs the permissions extension's Node test suite.

Reload or restart Pi after changing an extension, its configuration, or a subagent definition. A running subagent is not affected by later configuration changes.

Extensions

`minimal-footer`

Read the full file on GitHub · 68 lines

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.

2d ago First seen · 68 lines · 1,323 tokens per session scan A 639f43c0aaa8

Subscribe to this mod's changes

dotfiles AGENTS.md is an instructions file published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 9d ago), licensed MIT. It adds 1,323 tokens to every session, about $0.0066 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.

Testing

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

dotfiles AGENTS.md