Borrowing it
Nothing to install: this file belongs to OutlitAI/outlit-sdk. 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/OutlitAI/outlit-sdk/main/AGENTS.mdgit clone --depth 1 https://github.com/OutlitAI/outlit-sdkWrote 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/outlitai/outlit-sdk/agents-md)<a href="https://agentmods.dev/instructions/outlitai/outlit-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/outlitai/outlit-sdk/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/outlitai/outlit-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/outlitai/outlit-sdk/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 | $0.01670 | $0.01670 |
| Opus 5.5 | $0.00668 | $0.00668 |
| Sonnet 5.5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
outlit-sdk 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 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.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outlit SDK
Agent workflow
- Follow the user's requested outcome through implementation and relevant verification when they ask for a change. A request to review or explain stays read-only unless it also authorizes fixes. Reuse decisions and authorization already given in the conversation.
- Inspect discoverable facts and make routine, reversible implementation choices. Ask only for unresolved decisions that materially affect scope, behavior, risk, or external actions; continue independent authorized work while waiting. Prepare a concrete result before seeking any remaining release approval.
- Use skills that materially help the task. These repository workflow rules take precedence over generic skill process defaults, subject to system/developer instructions and the user's request. Skill discovery, a planning template, or a finishing menu must not create an extra approval gate. If a skill blocks progress, cite its exact file and instruction and explain the unresolved requirement.
- Scale planning to the work. Use a short internal plan for a clear change; write a durable plan for meaningful sequencing, contracts, migrations, or long work. An authorized implementation task continues after planning. Keep changes cohesive and preserve unrelated work; add abstractions only for a current requirement or demonstrated consumer.
- When delegation is available and permitted by the session, use bounded specialists for independent work that benefits from parallel execution or fresh review. Keep one lead responsible for integration and final evidence. Give writers separate ownership and reviewers distinct questions. Reuse passing checks and stop review when requested risks are covered; repeat only for relevant changes or unresolved findings.
- Match verification to the claim. Use relevant tests and required CI for code; inspect or render documentation, copy, and visual changes as appropriate. Do not add tests that only restate the edit or repeat passing checks on unchanged inputs. Keep product-specific security, data, and release gates.
- Report the outcome, evidence, and remaining limits concisely. Identify the checked revision and environment when they matter. For long reviews, save detailed findings to a linked artifact. A running server, empty screen, queued job, or green build alone does not prove a requested user flow or deployment succeeded.
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 · +7 lines · +178 tokens per session bc0363078f3d
- 1mo ago Changed · +10 lines · +428 tokens per session ae88a3e5ef1f
- 2mo ago First seen · 82 lines · 1,064 tokens per session scan A 6b7b3f96b314
outlit-sdk AGENTS.md is an instructions file published in the GitHub repository OutlitAI/outlit-sdk (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,670 tokens to every session, about $0.0067 per session on Opus 5.5. 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).
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.