What is bloom AGENTS.md?

A set of repository instructions for contributing to Bloom, including its architecture, ownership boundaries, development process, and verification rules. Bloom's documentation mentions wallets and Solana, a blockchain platform, as part of the project.

Use it when changing the Bloom repository or related repositories and when deciding which development and testing guidance to follow.

It tells an agent which repository owns each responsibility and which documents are authoritative. This helps prevent changes that cross process, wallet, signing, or approval boundaries incorrectly.

How bloom-directory/bloom configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to bloom-directory/bloom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bloom-directory/bloom/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bloom-directory/bloom

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bloom-directory/bloom/agents-md/github.svg)](https://agentmods.dev/instructions/bloom-directory/bloom/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bloom-directory/bloom/agents-md"><img src="https://agentmods.dev/badge/instructions/bloom-directory/bloom/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bloom-directory/bloom/agents-md"><img src="https://agentmods.dev/badge/instructions/bloom-directory/bloom/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 952 This file is loaded in full into every session.

When invoked 952 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00952	$0.00952
Opus 5.5	$0.00381	$0.00381
Sonnet 5.5	$0.00190	$0.00190
Haiku 4.5	$0.00095	$0.00095

Measured 3d ago against content hash e556d0840393, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bloom 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 3d 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.

AGENTS.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bloom contributor and agent guide

Use DEVELOPMENT.md for setup and cross-repository workflows, and TESTING.md for validation gates. The instructions exposed inside a running VFS are a separate operator contract in agent-guidance.md.

Authority and ownership

Read the relevant architecture before changing a cross-process contract:

Historical plans and implementation logs are evidence, not authority, when they conflict with current code or the documents above.

Machine talks to Broker; only Broker talks to Signer. Fix an invariant in its owning repository:

Repository	Owns
`bloom` (Machine)	CLI, VFS, Petals, public projections, staging, simulation, broadcast, reconciliation
`bloom-broker`	Ceremony verification, policy semantics, Sealed Approvals, authorization
`bloom-signer`	Encrypted wallet custody, derivation, counters, replay protection, cryptographic signing

Preserve these boundaries:

Never add Bloom wallet secrets, a wallet-signing implementation, local approval authority, or a direct Signer connection to Machine. This custody rule does not prohibit authenticated transport identities or Petal-owned application keys described in the wallet architecture.
Never use a cached projection, list position, address alias, or Petal claim as authority. Account-sensitive operations bind the exact public-key fingerprint and derivation path in KeyRef; ambiguity fails closed.
Never restore retired Machine keystores, approval stores, or local signer fallbacks when an authority service is unavailable.
Wallet secret input belongs in the Broker-hosted ceremony, not Machine RPC, VFS writes, shell arguments, environment variables, or logs. Acceptance fixtures use disposable test inputs through the reviewed test harness.
Development mode may share a UID, but must retain the real process and protocol boundaries. triad-dev-harness is forbidden in release bundles.
Solana is native Machine functionality. Preserve its genesis checks, exact account selection, and reconciliation after ambiguous sends; never blindly retry a broadcast.

Read the full file on GitHub · 84 lines

Changes

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.

3d ago Changed · +3 lines · +39 tokens per session e556d0840393
6d ago Changed · +2 lines · +38 tokens per session 2058f6ce98b8
1mo ago Changed · +1 lines · +9 tokens per session cb5631e39aa1
1mo ago First seen · 78 lines · 866 tokens per session scan A b2bd90a48f5c

Subscribe to this mod's changes

bloom AGENTS.md is an instructions file published in the GitHub repository bloom-directory/bloom (26 stars, last pushed yesterday), licensed MIT. It adds 952 tokens to every session, about $0.0038 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 2026-09-15.

Web3 and blockchain agent-skills ai-agents claude-code-plugin codex-plugin gemini-cli-extension

bloom AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bloom AGENTS.mdbloom-directory/bloom	Instructions file	26	yesterday	MIT	A	952	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bloom: Instructions file for Codex