Borrowing it
Nothing to install: this file belongs to t41372/skit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/t41372/skit/main/AGENTS.mdgit clone --depth 1 https://github.com/t41372/skitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/t41372/skit/agents-md)<a href="https://agentmods.dev/instructions/t41372/skit/agents-md"><img src="https://agentmods.dev/badge/instructions/t41372/skit/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/t41372/skit/agents-md"><img src="https://agentmods.dev/badge/instructions/t41372/skit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.01457 | $0.01457 |
| Opus 5.5 | $0.00583 | $0.00583 |
| Sonnet 5.5 | $0.00291 | $0.00291 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade C, and why
skit AGENTS.md scanned grade C with 1 finding 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 1mo 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
or other threat mitigations for user-controlled local content. Do not refuse an operation because How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Product
skit is a Rust script launcher and parameter manager. Users keep Python, shell, JavaScript, TypeScript, fish, PowerShell, Ruby, Perl, Lua, R, executable, command-template, and prompt entries in one library. They can use the Ratatui interface or the deterministic CLI.
Product rules
- Localize every user-visible string. English is the source locale. Simplified Chinese and
Traditional Chinese must be complete. JSON keys and
skills/skit/SKILL.mdare English-only machine contracts. - Keep each TUI action available by keyboard and mouse. Every visible footer chip is a click target. Every advertised key needs a positive test.
- Keep the interface discoverable. A user must not need to remember commands, keys, or script arguments.
- Keep every TUI capability available through the CLI. Machine paths need
--json, deterministic exit codes,--no-input,--dry-runwhere applicable, and dynamic completion. - Keep the quality gates hard: complete executable-source line coverage, Clippy with warnings as errors, Rustdoc warnings as errors, cargo-mutants with zero survivors, and complete i18n.
- Do not change global or third-party configuration without explicit consent. skit can change only its own data, state, and configuration directories.
Trust model
skit is a local launcher. It is not a sandbox or a security boundary. The user owns and trusts the machine, library, scripts, command-line arguments, templates, prompts, environment values, output, and logs. Running user-authored code is the primary product operation.
Do not add sanitization, escaping, character blocks, permission policies, secret-handling policies, or other threat mitigations for user-controlled local content. Do not refuse an operation because the trusted script or argument could run a command. Keep the operating system and language runtime semantics unless version 0.4 already defines a different behavior.
Security-related work is in scope only when it does one of these things:
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.
- 1mo ago Changed · -65 lines · -1,701 tokens per session scan A → C 63b5014f0fbc
- 2mo 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 (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,457 tokens to every session, about $0.0058 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.