What is BisonNotes-AI AGENTS.md?

Project instructions for BisonNotes-AI, a native iPhone and Apple Watch application built with Xcode. They explain what a Linux cloud coding environment can and cannot do for the project.

Use them to guide Swift code review and editing, linting, syntax checks, project setup, and Git work from Linux.

They prevent the coding agent from attempting builds or tests that require macOS, Xcode, or the iOS Simulator when those tools are unavailable.

BisonNotes-AI AGENTS.md — Instructions file by bisonbet

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/bisonbet/bisonnotes-ai/agents-md

Clone the repo

git clone --depth 1 https://github.com/bisonbet/BisonNotes-AI

Made for: Codex, OpenCode.

Per session 1,184 This file is loaded in full into every session.

When invoked 1,184 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	$0.01184	$0.01184
Opus 5	$0.00592	$0.00592
Sonnet 5	$0.00237	$0.00237
Haiku 4.5	$0.00118	$0.00118

Measured 3d ago against content hash 62a9d1e75959, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

BisonNotes-AI 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 3d 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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Platform constraints

This is a native iOS/watchOS Xcode project. It requires macOS with Xcode 15+ to build, run the iOS Simulator, and execute unit/UI tests. On a Linux Cloud Agent VM:

Cannot build: xcodebuild is macOS-only.
Cannot run: iOS Simulator requires macOS.
Cannot run unit/UI tests: Tests require Xcode and the simulator.
Cannot resolve SPM dependencies via Xcode: The project uses Xcode-managed SPM (no standalone Package.swift), and packages depend on Apple-only frameworks.

What you CAN do on Linux

Lint: Run swiftlint lint against Swift files (requires LINUX_SOURCEKIT_LIB_PATH set; see below).
Syntax-check: Run swiftc -parse <file.swift> to validate Swift syntax (works for files without Apple framework imports).
Code review/editing: Read, search, and edit all Swift source files, Core Data model XML, plists, entitlements, etc.
Git operations: Full git workflow including branching, committing, and pushing.

Environment setup (Cloud Agent)

The Cloud Agent environment is defined by .cursor/environment.json, whose install step runs .cursor/install.sh. That script is idempotent and:

Installs the Swift OS dependencies (libcurl, libpython, etc.).
Installs Swift 6.3.3 via Swiftly at ~/.local/share/swiftly/.
Installs SwiftLint 0.58.2 at /usr/local/bin/swiftlint.
Appends a guarded block to ~/.bashrc (also picked up by login shells because ~/.profile sources ~/.bashrc) that sets:
Swiftly env: . "${SWIFTLY_HOME_DIR:-$HOME/.local/share/swiftly}/env.sh"
SourceKit path: export LINUX_SOURCEKIT_LIB_PATH=... (auto-computed from the installed toolchain)

To change the pinned Swift or SwiftLint version, edit the SWIFT_VERSION / SWIFTLINT_VERSION variables at the top of .cursor/install.sh.

Running SwiftLint

cd "BisonNotes AI/BisonNotes AI"
swiftlint lint                    # Full lint with all details
swiftlint lint --reporter summary # Summary table only

Read the full file on GitHub · 98 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.

3d ago First seen · 98 lines · 1,184 tokens per session scan A 62a9d1e75959

Subscribe to this mod's changes

BisonNotes-AI AGENTS.md is an instructions file published in the GitHub repository bisonbet/BisonNotes-AI (11 stars, last pushed 3d ago), licensed MIT. It adds 1,184 tokens to every session, about $0.0059 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.

Mobile

BisonNotes-AI AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Cursor Cloud specific instructions

Platform constraints

What you CAN do on Linux

Environment setup (Cloud Agent)

Running SwiftLint

What this file has done since we first saw it

Other instructions, from other repositories

MobiAI-Core CLAUDE.md

freetube CLAUDE.md

ConsultMe CLAUDE.md

claude-status CLAUDE.md

DensityToggle CLAUDE.md

phone-mcp CLAUDE.md