ai-workflow-starter AGENTS.md

ai-workflow-starter AGENTS.md is an instructions file for Codex, OpenCode from JSMike/ai-workflow-starter. It costs 2,059 tokens per session, scanned A, original, MIT.

A set of repository instructions for an auditable workflow in which coding-agent work is clarified, tracked, documented, and easy to resume. It uses an issues folder and records plans, decisions, progress, and verification notes.

In plain words
What is it for?
Use it to guide agents working in the JSMike/ai-workflow-starter repository. It is for managing issue intake, project details, work records, and handoffs.
Why use it?
It prevents important context from being lost between sessions or agents. It also makes unfinished work and the evidence for completed work easier to review.

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/jsmike/ai-workflow-starter/agents-md
Clone the repo
git clone --depth 1 https://github.com/JSMike/ai-workflow-starter

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 ai-workflow-starter AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jsmike/ai-workflow-starter/agents-md.svg)](https://agentmods.dev/instructions/jsmike/ai-workflow-starter/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jsmike/ai-workflow-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/jsmike/ai-workflow-starter/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,059 This file is loaded in full into every session.
When invoked 2,059 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 $0.02059 $0.02059
Opus 5 $0.01030 $0.01030
Sonnet 5 $0.00412 $0.00412
Haiku 4.5 $0.00206 $0.00206

Measured 3d ago against content hash 48dca2d8e1fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-workflow-starter 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 3d 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 · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical guidance for AI agents working in this repository.

This file is the source of truth for project conventions and the AI issue workflow.

Project Overview

This project requires an auditable AI workflow. Agents are expected to follow the process below so work is traceable, reviewable, and easy to resume across sessions or tools.

The user expects agents to:

  • Clarify vague or underspecified requests before implementation.
  • Track actionable work in .issues/.
  • Keep plans, decisions, progress, and verification notes current.
  • Preserve enough context for another agent or human to continue without reconstructing the conversation.
  • Avoid untracked work, skipped session logs, and premature done status.

Project Details

Fill this section in for the target project. If the project already has an AGENTS.md, merge this workflow guidance into the existing file instead of replacing project-specific instructions.

Agents should keep these details current when they discover or change them:

  • Project purpose:
  • Primary runtime and package manager:
  • Build, test, lint, and dev commands:
  • Key source and test directories:
  • Environment variables and local setup:
  • Deployment, sync, or background job notes:
  • Project-specific conventions and constraints:

Core Workflow Principle

Every task must be tracked in .issues/ once it becomes actionable work.

Actionable work includes:

  • Code, documentation, configuration, design, or workflow changes.
  • Creating or updating issue records, plans, QA instructions, or summaries.
  • Repository investigation that produces decisions, plans, recommendations, or implementation steps.
  • Follow-up requests that change scope, acceptance criteria, verification, or handoff context.

Casual questions or discussion do not require an issue unless they become planned work or need durable follow-up.

The .issues/ audit trail should preserve the request, clarifications, plan, delivered changes, verification path, and remaining next steps.

Read the full file on GitHub · 223 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. 3d ago First seen · 223 lines · 2,059 tokens per session scan A 48dca2d8e1fd

Subscribe to this mod's changes

ai-workflow-starter AGENTS.md is an instructions file published in the GitHub repository JSMike/ai-workflow-starter (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,059 tokens to every session, about $0.0103 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.