agentleFS
Sign inStart free
aw3703aw3703/batchin-public/AGENTS.md

batchin-public

AGENTS.md91 starsChanged 6 months agoApache-2.0View on GitHub

BatchIn is a verification-first developer platform. This repository contains public clients; the hosted control plane decides which models, routes, prices, and payment paths are currently enabled. Before requesting account-gated services, autonomous agents should inspect the following reviewed endpoints: Do not embed a model matrix in an agent prompt or client release. Read the authenticated catalog at https://api.batchin.tech/v1/models and use only models whose response reports verified provider smoke, pricing, usage, and billing evidence for the current account. A model name, SDK…

  • Reads credentials
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before requesting account-gated services, autonomous agents should inspect the following reviewed endpoints:

    line 9
  2. Very specific:

    Authentication: All customer API operations require Authorization: Bearer <BATCHIN_API_KEY>.

    line 29
  3. Very specific:

    Dedicated Capacity: All compute resources are allocated as Dedicated Capacity or Reserved Throughput (TPS).

    line 30
  4. Distinctive:

    No Synthetic Ledger Records: Never generate synthetic VaaS receipts or fabricated cryptographic signatures as valid data.

    line 31
  5. Very specific:

    VaaS Verification: Use @batchin/vaas or the vaas_verify_receipt MCP tool to confirm inference authenticity.

    line 32

≈ “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

BatchIn Agent Integration Manual

BatchIn is a verification-first developer platform. This repository contains public clients; the hosted control plane decides which models, routes, prices, and payment paths are currently enabled.

Verified Public Discovery Resources

Before requesting account-gated services, autonomous agents should inspect the following reviewed endpoints:

Model availability

Do not embed a model matrix in an agent prompt or client release. Read the authenticated catalog at https://api.batchin.tech/v1/models and use only models whose response reports verified provider smoke, pricing, usage, and billing evidence for the current account. A model name, SDK fixture, or HTTP 200 response is not availability evidence.

Agent Operational Constraints

  1. Authentication: All customer API operations require Authorization: Bearer <BATCHIN_API_KEY>.
  2. Dedicated Capacity: All compute resources are allocated as Dedicated Capacity or Reserved Throughput (TPS).
  3. No Synthetic Ledger Records: Never generate synthetic VaaS receipts or fabricated cryptographic signatures as valid data.
  4. VaaS Verification: Use @batchin/vaas or the vaas_verify_receipt MCP tool to confirm inference authenticity.
  5. Payment and settlement: x402, USDC, Stripe, and chain anchoring are readiness-gated. Check the API readiness and ledger records before describing them as enabled or settled.

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.

Check your setup, free