Borrowing it
Nothing to install: this file belongs to Brainwires/rullama-framework. 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/Brainwires/rullama-framework/main/AGENTS.mdgit clone --depth 1 https://github.com/Brainwires/rullama-frameworkWrote 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/brainwires/rullama-framework/agents-md)<a href="https://agentmods.dev/instructions/brainwires/rullama-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/brainwires/rullama-framework/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/brainwires/rullama-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/brainwires/rullama-framework/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 | $0.01809 | $0.01809 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
rullama-framework 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 yesterday.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file gives coding agents project-specific context. Keep it short and update it when workflows change.
Project Overview
- Primary app or package: the
rullamaRust workspace (crates/) and its Deno/TypeScript port underdeno/— 27 JSR packages published as@rullama/*(deno/packages/*). - Main entry points: each
deno/packages/<name>/mod.ts(plus the subpathexportsin that package'sdeno.json); Rust crates undercrates/<name>/src/lib.rs. - Important directories:
deno/packages(the published packages),deno/tests(cross-package integration tests),deno/examples(deno runsamples),deno/docs,deno/fixtures(Rust↔Deno wire goldens),crates/(Rust).
Architecture Notes
- Module boundaries:
@rullama/coreis the zero-dependency type layer; every other package depends on it and never on a sibling except as declared indeno/README.md's dependency diagram. Sibling imports use the bare@rullama/<name>specifier and resolve to the local workspace member. - Generated or vendored code: none in
deno/;deno/fixtures/*.jsonare goldens read as text. - Sensitive areas:
deno/packages/tool-builtins(bash/file/git/web execution),deno/packages/permission(policy enforcement),deno/packages/provider(API keys, request signing),deno/packages/mcp-serveranda2a(inbound protocol handling).
Commands (Deno, run from deno/)
- Install: nothing to install —
denoresolves the import map;fallowmust be on PATH (npm i -g falloworcargo install fallow-cli). - Build: no build step (JSR publishes TypeScript sources).
- Test:
deno task test(packages/ + tests/); one package:deno test -A packages/<name>/. - Typecheck or lint:
deno task check= fmt --check + lint + type-check (packages, tests, examples) +deno task doc-lint(JSDoc on every export of the 74 published entrypoints)- tests — what CI runs;
deno task check:fixauto-fixes formatting and fixable lint.
- tests — what CI runs;
- Publishing (like denext, one package per tag): bump the changed package's
deno.jsonversion, commit, thencd deno && deno task publish:changes --push— it finds the packages whose version is not on JSR, tags them<package>-v<version>in dependency order and waits for eachpublish-deno.ymlrun (OIDC provenance). Without--pushit only reports;--bump patchbumps packages that changed without a bump.deno/scripts/publish.sh [--package <name>]is the manual fallback.deno task jsr:scoresrefreshesdeno/docs/jsr-scores.md. - Coverage for fallow's CRAP score:
deno task coverage:fallow(writesdeno/coverage/coverage-final.json, which the pre-commit hook passes tofallow audit).
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.
- yesterday First seen · 108 lines · 1,809 tokens per session scan A aaaeca0f5a5c
rullama-framework AGENTS.md is an instructions file published in the GitHub repository Brainwires/rullama-framework (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,809 tokens to every session, about $0.0090 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 2026-09-15.
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.
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.
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).