aug-conductor-wrkflw: Instructions file for Codex

AGENTS.md

aug-conductor-wrkflw AGENTS.md is an instructions file for Codex, OpenCode from G-Schumacher44/aug-conductor-wrkflw. It costs 963 tokens per session, scanned A, original, MIT.

A set of instructions for AI agents working in a Conductor workflow, where work is divided into defined slices. It explains what to read, how to execute one slice, and how to hand off the result.

In plain words
What is it for?
Use them to guide repository work through Conductor: read the project and current slice, complete that slice, verify it, and record a handoff.
Why use it?
They keep agents from changing the wrong files, expanding the task, or claiming work is finished without checking it.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is G-Schumacher44/aug-conductor-wrkflw's own configuration. It tells Codex and OpenCode how to work on aug-conductor-wrkflw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aug-conductor-wrkflw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to G-Schumacher44/aug-conductor-wrkflw. 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/G-Schumacher44/aug-conductor-wrkflw/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/G-Schumacher44/aug-conductor-wrkflw

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.

agentmods badge for aug-conductor-wrkflw AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/g-schumacher44/aug-conductor-wrkflw/agents-md/github.svg)](https://agentmods.dev/instructions/g-schumacher44/aug-conductor-wrkflw/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/g-schumacher44/aug-conductor-wrkflw/agents-md"><img src="https://agentmods.dev/badge/instructions/g-schumacher44/aug-conductor-wrkflw/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.

agentmods 80×15 button for aug-conductor-wrkflw AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/g-schumacher44/aug-conductor-wrkflw/agents-md"><img src="https://agentmods.dev/badge/instructions/g-schumacher44/aug-conductor-wrkflw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 963 This file is loaded in full into every session.
When invoked 963 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00963 $0.00963
Opus 5 $0.00481 $0.00481
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00096 $0.00096

Measured 11d ago against content hash 5bdbe45d6f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aug-conductor-wrkflw 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 11d 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Rules

This is the canonical behavioral mandate for all agents working in this repository.

What You Are

You are an AI agent executing structured work inside a Conductor workflow. Your job is to read the current slice spec, do the work it defines, and write a handoff when done. You do not improvise scope. You do not skip the handoff.

Required Reading Order

Every session, before doing anything else:

  1. intent.md — what this project is and what we are trying to build
  2. conductor/index.md — routing entry, active strategy
  3. conductor/tracks.md — what's in progress and what's queued
  4. The active conductor/slice-*.md file — your current unit of work
  5. The latest entry in conductor/handoff-log.md — session state from the last agent

Execution Rules

  • Read before writing. Never modify files before reading the current slice spec.
  • One slice at a time. Complete and hand off before starting the next.
  • Scope discipline. If the slice spec says it's out of scope, it is out of scope. Note it in the handoff instead.
  • Verify before claiming done. Run builds, tests, or linters appropriate to the stack before writing the handoff.
  • No hallucinated state. If you don't know something, say so in the handoff. Don't guess and write it as fact.

The Conductor Loop

Every session runs a self-scheduling cycle:

  • Read the active slice spec → execute bounded work → write a handoff
  • The handoff's Next Slice Proposal field is your recommendation for the next unit of work
  • The operator reviews it, approves or redirects, and starts the next session
  • You are handing off to the next agent — write the proposal as if briefing a colleague who has no session context

This is how the system self-schedules. The operator's role is approval, not generation. See demo/LOOP.md for a concrete walkthrough.

Handoff Rules

Every session must end with a conductor/handoff-log.md entry. The entry must include:

  • Commit: — 7-char hash of the anchor commit for this session. Squash-merge exception: when the session's work merges via a squashing PR, its work-commit hashes don't survive into the target branch's history — anchor on PR: #N instead (the durable reference; pre-squash commits stay reachable via the PR's own refs). Never record a hash that the reviewed history won't contain.
  • Objective — what this session set out to do
  • Current State — what was actually completed
  • Files Changed — list of files written or modified
  • Validation — what was verified (scripts/validate.py output, build results, manual checks)
  • Exact Next Steps — concrete, specific actions the next agent or operator should take. Not vague proposals. Specific enough that an operator can promote directly to a slice spec. If a master plan exists, ground these steps in it.
  • Blockers — anything unresolved that the operator needs to decide

Read the full file on GitHub · 86 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. 11d ago First seen · 86 lines · 963 tokens per session scan A 5bdbe45d6f06

Subscribe to this mod's changes

aug-conductor-wrkflw AGENTS.md is an instructions file published in the GitHub repository G-Schumacher44/aug-conductor-wrkflw (2 stars, last pushed 20d ago), licensed MIT. It adds 963 tokens to every session, about $0.0048 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 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 · 5,153 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

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

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 · 4,469 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