agentmods.dev

tuisky AGENTS.md

Project instructions for TuiSky, a terminal-based Bluesky client built with Bun, React, and Gridland. They describe the project's commands, technology, tests, and release process.

In plain words
What is it for?
Use them when developing TuiSky, running its development or build commands, executing tests, or preparing macOS release archives and Homebrew updates.
Why use it?
They give a coding agent the project context needed to make changes without guessing how to run, build, test, or release the application.

Instructions file for CodexOpenCode

5 2mo ago A scan 1,207 tokens original MIT
View the source file blackmichael/tuisky
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/blackmichael/tuisky/agents-md
Clone the repo
git clone --depth 1 https://github.com/blackmichael/tuisky

Made for: Codex, OpenCode.

Per session 1,207 This file is loaded in full into every session.
When invoked 1,207 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.

ModelPer sessionOnce invoked
Fable 5 $0.01207 $0.01207
Opus 5 $0.00603 $0.00603
Sonnet 5 $0.00241 $0.00241
Haiku 4.5 $0.00121 $0.00121

Measured 2d ago against content hash d38bc550e2fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tuisky 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 · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file gives repo-specific guidance for coding agents working in this project.

Purpose

TuiSky is a terminal Bluesky client built with Bun + React + Gridland (a library built on top of OpenTUI). The codebase is small and UI-heavy. Most changes affect keyboard interaction, terminal layout, or optimistic state updates against the AT Protocol API.

Tech Stack

  • bun
  • react
  • @gridland/bun
  • @atproto/api

Core Commands

Install:

bun install

Run app:

bun run dev

Show CLI help or version without starting the TUI:

bun run dev -- --help
bun run dev -- --version

Build:

bun run build

Build with an explicit app version embedded at compile time:

bun run build -- --version 1.2.3

Build macOS release archives for GitHub Releases and Homebrew:

bun run build:release -- --version 1.2.3

Test:

bun test

Release Flow

  • GitHub tag pushes matching v* trigger .github/workflows/release.yml.
  • The workflow builds native darwin-arm64 and darwin-x64 archives, publishes them to the GitHub Release, and writes checksums.txt.
  • After publishing assets, the workflow opens a PR against blackmichael/homebrew-tap updating Formula/tuisky.rb.
  • The release workflow requires the HOMEBREW_TAP_GITHUB_TOKEN secret with permission to push branches and open PRs in blackmichael/homebrew-tap.

Repo Shape

  • src/App.tsx App shell, providers, router, global quit handling.
  • src/screens Top-level screens: login, timeline, post detail, profile.
  • src/components Shared terminal UI components like post cards, reply lists, profile header, status bar.
  • src/api Thin wrappers around @atproto/api.
  • src/state Context/reducer state for auth, navigation, and timeline.
  • src/lib Pure helpers and unit tests. Prefer putting logic here when it can be tested outside the terminal renderer.

Working Norms

  • Keep terminal layout deterministic. Dynamic wrapping can easily break row budgeting and hide engagement rows.
  • Prefer fixed-height or explicitly budgeted list rows for scrolling UIs.
  • When changing list rendering, check both timeline and reply list behavior.
  • Keep shared rendering pieces shared. Examples: PostMeta, PostEngagement, ProfileMeta, ProfileEngagement.
  • For behavior-heavy changes, extract pure helpers into src/lib and add bun test coverage.

Read the full file on GitHub · 136 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.

  1. 2d ago First seen · 136 lines · 1,207 tokens per session scan A d38bc550e2fd

Subscribe to this mod's changes

tuisky AGENTS.md is an instructions file published in the GitHub repository blackmichael/tuisky (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,207 tokens to every session, about $0.0060 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.

atmosphereatprotoatprotocolbluesky
Related

Other instructions, from other repositories

atproto-skills CLAUDE.md

Instructions for ngerakines/atproto-skills, covering authoring guide: atproto-skills, 1. skill anatomy, polyglot skills (optional shape), 2. progressive disclosure and 3. writing effective description fields.

ngerakines/atproto-skills · 3,236 tokens

bluesky-mcp AGENTS.md

AGENTS.md instructions for sandraschi/bluesky-mcp, covering bluesky-mcp — agent guide, standards, key files and quick ref.

sandraschi/bluesky-mcp · 338 tokens

bluesky-mcp CLAUDE.md

Claude Code instructions for sandraschi/bluesky-mcp, covering bluesky-mcp — claude / agent context, do, don't and commands.

sandraschi/bluesky-mcp · 166 tokens

wordpress-atmosphere AGENTS.md

AGENTS.md instructions for Automattic/wordpress-atmosphere, covering atmosphere plugin, directory structure, commands, environment and php tests (require wp-env running).

Automattic/wordpress-atmosphere · 2,916 tokens

bluesky-mcp copilot-instructions.md

Copilot instructions for sandraschi/bluesky-mcp, covering github copilot instructions for bluesky-mcp and session context (bluesky mcp).

sandraschi/bluesky-mcp · 179 tokens

skyreader AGENTS.md

AGENTS.md instructions for disnet/skyreader, a project described as: An RSS reader for the AT Protocol.

disnet/skyreader · 4 tokens