openaugi AGENTS.md

Repository instructions for a specific software project, including where to resume work, how its parts are organized, and how to install and document changes.

In plain words
What is it for?
Use them when working in the bitsofchris/openaugi codebase, especially when finding plans, related repositories, tests, documentation, or the next unfinished task.
Why use it?
They give a coding agent the project's working context so it can continue consistently between sessions and follow its testing and documentation expectations.

Instructions file for CodexOpenCode

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/bitsofchris/openaugi/agents-md
Clone the repo
git clone --depth 1 https://github.com/bitsofchris/openaugi

Made for: Codex, OpenCode.

Per session 1,817 This file is loaded in full into every session.
When invoked 1,817 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.

ModelPer sessionOnce invoked
Fable 5 $0.01817 $0.01817
Opus 5 $0.00908 $0.00908
Sonnet 5 $0.00363 $0.00363
Haiku 4.5 $0.00182 $0.00182

Measured 2d ago against content hash 8e1478ea0bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openaugi 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 2d 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You build software as a senior staff engineer who wants a code base that is modular, extensible, simple, well tested, and reliable. You do not make assumptions but clarify trade offs and do web searches to understand pragmatic best practices. You document as you go - keeping docs up-to-date from the overall ARCHITECTURE.md linking to other docs when needed to describe features and why. You write unit tests but also make sure we are able to test end to end either with integration or mocking components. You the agent are constantly improving your ability to work in this codebase - document common patterns or skills, build CLI tools or save scripts/ commands needed to work in this repo.

Where to resume (new session entry point)

  1. Start at docs/plans/master-plan.md — the long-running sequence (M1…M8) with a STATUS/LEFT OFF header that MUST be updated every session. Other docs in docs/plans/ are per-milestone detail; done plans move to docs/plans/done/.
  2. System manual for the write-back loop: docs/reference/review-pass.md (augi_tags, routing, capture grammar, views).
  3. Vault-side entry (Chris's daily driver): View - Dashboard.md under <vault>/OpenAugi/Views/ — regenerated every review pass, links everything. Two verbs: "run the review pass" (full loop) · "process the dashboard" (execute nomination answers only).

Where things live

This repo is public. Chris's vault is not. Before committing any doc, ask: does this contain actual content from the vault, or just describe the system that operates on it?

Fine to commit: category/taxonomy names, tag names, schema fields, config shapes — the system-level vocabulary (e.g. "an area/health container exists," "clustering produces life-area buckets").

Never commit: real note titles or content, real routing/nomination decisions, actual cluster contents or counts, personal reflections, post drafts, session handoffs that quote real vault data — i.e. anything that is output from the second brain rather than a description of it. If a doc is reporting what specifically got routed/clustered/decided on Chris's real data, it belongs in docs/scratch/ (gitignored), not tracked.

Read the full file on GitHub · 134 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.

  1. 2d ago First seen · 134 lines · 1,817 tokens per session scan A 8e1478ea0bca

Subscribe to this mod's changes

openaugi AGENTS.md is an instructions file published in the GitHub repository bitsofchris/openaugi (128 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,817 tokens to every session, about $0.0091 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 2026-08-30.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens