What is ob-1 AGENTS.md?

A project memory file for Overbrilliant/ob-1, an AI coding agent. It records the codebase's tools, commands, important files, notes, checks, and known issues.

Use it to document a TypeScript/Bun project, point to key files and topic notes, and track validated behaviour and follow-ups.

It gives the agent a concise reference for how the project is organised and what has already been learned.

ob-1 AGENTS.md — Instructions file for Codex and OpenCode by Overbrilliant: A project memory file for Overbrilliant/ob-1, an AI coding…

Install

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.

agentmods

npx agentmods add instructions/overbrilliant/ob-1/agents-md

Clone the repo

git clone --depth 1 https://github.com/Overbrilliant/ob-1

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/overbrilliant/ob-1/agents-md.svg)](https://agentmods.dev/instructions/overbrilliant/ob-1/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/overbrilliant/ob-1/agents-md"><img src="https://agentmods.dev/badge/instructions/overbrilliant/ob-1/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 536 This file is loaded in full into every session.

When invoked 536 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00536	$0.00536
Opus 5	$0.00268	$0.00268
Sonnet 5	$0.00107	$0.00107
Haiku 4.5	$0.00054	$0.00054

Measured 4d ago against content hash 0cd5d0455004, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ob-1 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 4d 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 · 66 lines

What it actually says

AGENTS.md

OB-1 project memory index. OB-1 refreshes only the marked blocks below; edit freely outside them. Keep this concise (under ~200 lines). Put detailed notes in topic files and let episodes hold history.

Project index

Stack

TypeScript / Bun

Commands

run: bun run start

Key files

scripts/delivery-smoke.ts
src/cli/onboarding.ts
scripts/cli-flags-smoke.ts
src/memory/store.ts
src/agent/procs.ts
src/multimind/personas.ts
scripts/router-smoke.ts
src/agent/tools.ts
scripts/verify-smoke.ts
src/agent/loop.ts

Topic files

Detailed notes live in .ob1/topics/ when they exist.

Project memory

Validated checks

(none recorded yet)

Validated behavior checks

(none recorded yet)

Durable facts

(none promoted yet)

Quality patterns

(none promoted yet)

Failure patterns

(none recorded)

Known issues / follow-ups

(none recorded)

Episodes

Last episode: 2026-07-06T21-03-25-243Z-count-from-1-to-60-comma-separated-no-other- — Count from 1 to 60, comma separated, no other text. (2026-07-06)
Episode files: .ob1/episodes/*.md (local, ignored)

Conventions

Minimal runtime dependencies. Prefer Bun built-ins (bun:sqlite, fetch, node:*) where they fit. Heavy optional features such as browser_check load their packages lazily; keep new runtime dependencies justified and narrow.
Run bun run scripts/smoke.ts before committing memory/embedding changes.
Bundle-check with bun build src/index.ts --target=bun --outfile=/tmp/x.js (no tsc install).
Each layer is provider-/backend-swappable: sqlite-vec, tree-sitter, and other LLM providers are documented drop-in upgrades on a Node runtime.
See docs/planning/PROGRESS.md for the phased roadmap and docs/planning/ob1-plan.html for the full design.

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.

4d ago First seen · 66 lines · 536 tokens per session scan A 0cd5d0455004

Subscribe to this mod's changes

ob-1 AGENTS.md is an instructions file published in the GitHub repository Overbrilliant/ob-1 (9 stars, last pushed 8d ago), licensed Apache-2.0. It adds 536 tokens to every session, about $0.0027 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 2026-08-31.

LLM Memory and context ai-coding-agent bun cli coding-agent free

ob-1 AGENTS.md