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.
curl -O https://raw.githubusercontent.com/bloom-directory/bloom/master/AGENTS.mdgit clone --depth 1 https://github.com/bloom-directory/bloomWrote 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/bloom-directory/bloom/agents-md)<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.
<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>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 | $0.00866 | $0.00866 |
| Opus 5 | $0.00433 | $0.00433 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
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 today.
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 — 78 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:
- Triad process architecture
- Wallet architecture and account identity
- Solana native integration
- Triad release package
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-harnessis 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.
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.
- today First seen · 78 lines · 866 tokens per session scan A b2bd90a48f5c
bloom AGENTS.md is an instructions file published in the GitHub repository bloom-directory/bloom (23 stars, last pushed today), licensed MIT. It adds 866 tokens to every session, about $0.0043 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).