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/outlitai/outlit-sdk/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.svg" alt="Measured on agentmods" 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 | $0.01064 | $0.01064 |
| Opus 5 | $0.00532 | $0.00532 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outlit SDK
Monorepo for Outlit's TypeScript tracking SDKs (@outlit/core, @outlit/browser, @outlit/node) and CLI (@outlit/cli).
Tech stack
- Runtime: Bun (v1.3.9, set via
packageManagerin rootpackage.json) - Build: Turbo + tsup
- Linting/formatting: Biome
- Testing: Vitest (unit), Playwright (browser e2e)
- Releases: Changesets (
@changesets/cli) — stable releases and canary snapshots via GitHub Actions - Rust crate (
crates/outlit): released separately viarelease-plz
Project structure
packages/
core/ # Shared types and utilities (dependency of browser + node)
browser/ # Browser SDK with React and Vue bindings
node/ # Node.js server-side SDK
cli/ # CLI tool (Rust binary published via npm)
typescript-config/ # Shared tsconfig
Common commands
bun install # Install deps
bun run build # Build all packages (turbo)
bun run test # Run all tests
bun run typecheck # Type-check all packages
bun run lint # Lint with biome
bun run changeset # Create a changeset for your changes
Publishing rules
Never use workspace:* (or any workspace: protocol) in dependencies of published packages. Use concrete version ranges (e.g. "^1.1.0") instead. devDependencies may use workspace:* since they are excluded from published tarballs.
Why: Changesets uses npm publish under the hood (even in bun workspaces). npm publish does not resolve the workspace: protocol, so it leaks verbatim into the published tarball and breaks consumers — especially those using bun workspaces.
Bun workspaces resolve any matching version range to the local package, so concrete ranges like "^1.1.0" work identically to workspace:* during local development. Changesets' updateInternalDependencies: "patch" setting keeps these ranges in sync when dependency versions are bumped.
Changesets
- Config:
.changeset/config.json @outlit/core,@outlit/browser, and@outlit/nodeare linked — they version togetherupdateInternalDependencies: "patch"— changesets updates internal dep ranges on any bump- Canary snapshots publish on every push to
mainwhen unreleased changesets exist. Canary publication does not update stable npm tags, stable CDN assets, or CLI binaries. - Stable releases happen only when the bot-authored "Version Packages" PR is merged. Treat that merge as the production release button, not as routine repository maintenance.
- Before merging the Version Packages PR, run CI on its exact latest head by adding the existing
skip-changeloglabel (or removing and re-adding it after a bot update), wait forChangeset Check,Lint, Build & Test, andRust CI, then review the final package/version list. - For contracts coordinated with Core, use this order: merge the SDK source PR to
main, merge and promote the matching Core change to production, verify Core production, and only then merge the Version Packages PR. Do not publish the stable SDK merely because SDKmainor a canary is green. - Keep Core's default SDK-main drift validation fail-closed. Do not replace this release order with mutable counterpart branches or a bypass of either repository's normal drift checks.
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.
- 4d 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 1,064 tokens to every session, about $0.0053 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.