Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bulletxyz/bullet-bots/agents-mdgit clone --depth 1 https://github.com/bulletxyz/bullet-botsWrote 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/bulletxyz/bullet-bots/agents-md)<a href="https://agentmods.dev/instructions/bulletxyz/bullet-bots/agents-md"><img src="https://agentmods.dev/badge/instructions/bulletxyz/bullet-bots/agents-md.svg" alt="Measured on agentmods" 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 | $0.03972 | $0.03972 |
| Opus 5 | $0.01986 | $0.01986 |
| Sonnet 5 | $0.00794 | $0.00794 |
| Haiku 4.5 | $0.00397 | $0.00397 |
Grade A, and why
bullet-bots AGENTS.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# → writes ~/.config/bullet/id.key (base58 secret, 0600), prints address + faucet curl How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bullet-bots
Event-driven trading bot framework in Rust. Typed event bus, typed feeds per event kind, strategies implemented as actors. Pluggable exchange adapters and strategies connect through a shared harness that handles lifecycle, shutdown, and multi-source event dispatch.
Build & Test
cargo build # full workspace
cargo nextest run # unit + integration tests (default runner)
cargo test --doc # doctests only (nextest doesn't run these)
cargo clippy # lints (pedantic enabled)
cargo +nightly fmt # format (nightly required for import grouping)
First-time setup:
cargo install cargo-nextest --locked
The nextest config lives at .config/nextest.toml. CI should use the ci
profile (cargo nextest run --profile ci) which retries once and doesn't
fail-fast.
Validate a config without connecting:
cargo run --bin bb-bot -- validate --config config/simple-mm-example.toml
Generate a keypair (first time):
cargo run --bin bb-bot -- keygen --network testnet
# → writes ~/.config/bullet/id.key (base58 secret, 0600), prints address + faucet curl
Fund and onboard the account (first time). The faucet credits the on-chain
wallet (testnet only — on mainnet you fund the wallet with real
bridged/deposited assets instead); deposit then moves funds into the perp
margin account and initializes the trading account. Skipping the deposit makes
order placement fail with user_variants not found:
# Run the faucet curl printed by keygen, then:
cargo run --bin bb-bot -- deposit --network testnet --asset USDC --amount 5000
Run a bot (default: reads ~/.config/bullet/id.key):
cargo run --bin bb-bot -- run --config config/simple-mm-example.toml
Or point at an explicit key file / pass a key string for CI:
export BB_BULLET_KEY_FILE="/path/to/id.key" # preferred
# OR (base58 from Phantom/delegation export, or hex)
export BB_BULLET_PRIVATE_KEY="<base58-or-hex>" # fallback
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.
- 5d ago First seen · 378 lines · 3,972 tokens per session scan A 07de155c83a6
bullet-bots AGENTS.md is an instructions file published in the GitHub repository bulletxyz/bullet-bots (10 stars, last pushed 2mo ago), licensed MIT. It adds 3,972 tokens to every session, about $0.0199 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
NexusTrader CLAUDE.md
Instructions for Quantweb3-com/NexusTrader, covering claude.md, project overview, development commands, dependencies and setup and install with uv (package manager used in this project).
rustledger AGENTS.md
AGENTS.md instructions for rustledger/rustledger, covering rustledger development guidelines, project overview, architecture, rust-specific patterns and error handling strategy.
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.