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/t41372/skit/agents-mdgit clone --depth 1 https://github.com/t41372/skitWhat 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 | $0.03158 | $0.03158 |
| Opus 5 | $0.01579 | $0.01579 |
| Sonnet 5 | $0.00632 | $0.00632 |
| Haiku 4.5 | $0.00316 | $0.00316 |
Grade A, and why
skit 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What skit is
A script launcher and parameter manager. Users add scattered scripts — Python, shell, JS/TS, and a dozen kinds in all — into one library, then run them from skit's TUI menu or the CLI. Read README.md for more info.
Core design principles
1. Everything is i18n. Every user-visible string ships translated — English is the
original locale (msgids are the English source), all supported languages ship at 100%.
The one deliberate exemption: machine-facing surfaces — --json keys and the bundled
Agent Skill (skills/skit/SKILL.md) — are English-only contracts, not UI copy, and stay
outside the i18n gate.
2. Full mouse AND full keyboard interactivity. Every TUI action must be operable by mouse
alone and by keyboard alone. Footer chips are buttons (tui_footer.chip()): the visible key
hint is the click target, and every modal's key hints use the same chips — the mouse always
has a path. The keyboard side is enforced policy: every key a footer advertises must have a
positive pilot test.
Key grammar: a chord keeps one meaning per context class — Ctrl+E always opens $EDITOR
on the screen's current subject, Ctrl+N always creates the screen's primary object (a
script on the add step, an agent on a runner picker), Ctrl+T always inserts a value,
Ctrl+R re-runs/refreshes the screen's subject (the run form runs it; Script settings
resyncs its definitions from the script), and Ctrl+S saves/commits the screen's work
(the run form's save-as-preset included). Ctrl+A (cursor-home) and — while an Input has focus —
Ctrl+E (end-of-line) belong to the Input: screen chords for them are never
priority-bound; the chip is the path mid-edit.
Never bind a text-editing chord (Ctrl+K and friends) with priority=True on a screen
full of Inputs — the Input's own editing wins there, and the chip stays the mouse path.
The TUI is also responsive: tui_layout.py defines the shared size tiers (-w-narrow,
-h-short, -h-tiny, …) that Textual sets as classes on every screen, and all size
adaptation is CSS keyed off those classes — never per-screen width/height math in Python.
Footer rows wrap chip-by-chip (pills are unbreakable), modals never exceed the screen, and
new screens must degrade the same way.
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 · 205 lines · 3,158 tokens per session scan A 781da77b8b88
skit AGENTS.md is an instructions file published in the GitHub repository t41372/skit (6 stars, last pushed 4d ago), licensed MIT. It adds 3,158 tokens to every session, about $0.0158 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.
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.