agentleFS
BlazityBlazity/ai-workflow/packages/AGENTS.md

ai-workflow / packages

AGENTS.md18 starsChanged 58 days agoMITView on GitHub

Status: current Last-verified: 2026-09-25 Workspace packages shared by the worker and the dashboard. contracts holds cross-application shapes and constants; conditions evaluates predicates; costs prices provider usage; harness owns model policy and built-in compatibility profiles; prompts owns prompt composition; skills owns browser-safe product skill contracts and validation; workflow-graph owns the pure rules of a workflow definition; and agent-visibility owns the record of what one send gave a model and the clarification rounds, and never composes a prompt. These pure packages may…

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No app imports a package's internals: Every exports map exposes .

    line 22
  2. Very specific:

    Relative specifiers carry no extension: Write from "./domain", never from "./domain.js".

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Status: current Last-verified: 2026-09-25

packages/AGENTS.md

Workspace packages shared by the worker and the dashboard. contracts holds cross-application shapes and constants; conditions evaluates predicates; costs prices provider usage; harness owns model policy and built-in compatibility profiles; prompts owns prompt composition; skills owns browser-safe product skill contracts and validation; workflow-graph owns the pure rules of a workflow definition; and agent-visibility owns the record of what one send gave a model and the clarification rounds, and never composes a prompt. These pure packages may import another shared package only through its public entry point and never application infrastructure. ADR-001 owns the tiers.

The rules that bind

  • Source entry, no build. main, types and exports["."] all point at index.ts. There is no dist, no build script and no build:shared anywhere. Nitro and Next inline the source into their own bundles.
  • No app imports a package's internals. Every exports map exposes . only. Import a package through its public entry and add a re-export to its index.ts instead of deepening an import.
  • Relative specifiers carry no extension. Write from "./domain", never from "./domain.js". Nitro tolerates the .js form, webpack does not, and the failure appears only in the dashboard build.
  • Inlining relies on pnpm's symlinked node-linker. The Vercel tracer bundles a workspace .ts entry because its realpath resolves inside the workspace. A hoisted or isolated node-linker would send it looking for a dist entry, and there is none.
  • Each package typechecks itself. A package with no scripts drops silently out of pnpm -r typecheck, so each keeps a typecheck script and a strict tsconfig.json.
  • The test scripts name the packages they run, and they reach past packages/ into integrations/. pnpm run test:packages runs test in every shared package and every integration that owns a test script (the template, @integrations/example, included), and pnpm run test:packages:zod4 runs test:zod4 in the packages that carry a runtime zod dependency, every provider integration, the template, the SDK and the registry, whose conformance sweep parses every integration's schemas and so has to run under the zod production loads. The --filter lists in the root package.json are the one list; that sweep also covers the fixtures under integrations/_fixtures/, which have no suite of their own. Both scripts name packages with --filter, because --if-present over ./packages/* reports a package that owns no such script as passed. conditions has no test script at all and no suite in either run; that is a gap, not a decision recorded here. The test in scripts/ci/verify-changed.test.ts holds each named list equal to the packages that own the script, across both roots, so adding a package to a run is a deliberate edit and leaving one out is a failing test rather than a silent opt out.
  • Shared dependency versions live in the root catalog. Anything two projects declare goes on catalog:, enforced by scripts/gates/check-deps-consistency.mjs.

Area rules

.claude/rules/ carries what is true of one package only, loaded when a matching file is read: workflow-graph (what may live in the package, its suites and gates), contracts-requests (request body schemas), zod-bundle (the zod the worker bundle really runs), worker-settings (the settings registry), agent-visibility (the record of what one send gave a model), sandbox-agents (packages/prompts), and in integrations/, adapters, memory (mem0) and zod-bundle.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.