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/neolee/sct/agents-mdgit clone --depth 1 https://github.com/neolee/sctWhat 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 | $0.03068 | $0.03068 |
| Opus 5 | $0.01534 | $0.01534 |
| Sonnet 5 | $0.00614 | $0.00614 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade A, and why
sct 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Squirrel Configuration Tool (SCT) - Agent Guide
This document serves as a project overview and design record for AI agents working on the Squirrel (鼠须管) configuration GUI.
Project Overview
The goal is to provide a native macOS GUI for configuring the Squirrel input method, which traditionally requires manual editing of YAML files in ~/Library/Rime.
Core Design Philosophy
"Respect Rime Logic, Simplify User Operation"
- Non-Destructive: Never modify default
.yamlfiles. All changes must be written to.custom.yamlfiles under thepatch:key. - Native Experience: Use SwiftUI and macOS design patterns to make configuration feel like a first-class system setting.
- Transparency: Users should be able to see what YAML changes are being made.
Key Design Decisions
1. Dual-Layer Configuration Model
- Base Layer:
default.yaml,squirrel.yaml(Read-only). - Patch Layer:
default.custom.yaml,squirrel.custom.yaml(Read/Write). - Merged View: The GUI displays the result of merging the Patch Layer into the Base Layer.
2. Technology Stack
- Language: Swift 6.0+
- Framework: SwiftUI (Targeting latest macOS)
- YAML Engine: Yams for robust YAML parsing and serialization.
- Markdown Engine: MarkdownUI for rich help documentation rendering.
3. Configuration Merging Logic
Rime's patch system supports:
- Simple key-value replacement.
- Nested key access (e.g.,
style/font_face). - Array manipulation (though SCT currently focuses on full array replacement for simplicity).
4. Color Handling
Rime uses BGR (Blue-Green-Red) hex format (e.g., 0xBBGGRR). SCT must:
- Convert BGR to
SwiftUI.Colorfor the UI. - Convert
SwiftUI.Colorback to BGR for saving.
Functional Modules
General Settings
menu/page_size: Number of candidates.schema_list: Selection and ordering of input schemas.ascii_composer: Behavior of Shift/Caps Lock keys.
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 · 181 lines · 3,068 tokens per session scan A baba49d495e7
sct AGENTS.md is an instructions file published in the GitHub repository neolee/sct (52 stars, last pushed 5mo ago), licensed MIT. It adds 3,068 tokens to every session, about $0.0153 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.
Other instructions, from other repositories
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).
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.