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/jsmike/ai-workflow-starter/agents-mdgit clone --depth 1 https://github.com/JSMike/ai-workflow-starterWrote 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/jsmike/ai-workflow-starter/agents-md)<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>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 | $0.02059 | $0.02059 |
| Opus 5 | $0.01030 | $0.01030 |
| Sonnet 5 | $0.00412 | $0.00412 |
| Haiku 4.5 | $0.00206 | $0.00206 |
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.
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
donestatus.
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.
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.
- 3d ago First seen · 223 lines · 2,059 tokens per session scan A 48dca2d8e1fd
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.
Other instructions, from other repositories
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
Kanvas AGENTS.md
Instructions for XMihura/Kanvas, covering canvas workflow — agent instructions, critical rule, session protocol, 1. start of session — read the board and 2. pick a task.
delivery-loop CLAUDE.md
Instructions for blakemartz/delivery-loop, covering claude.md, what this is, the cardinal rule: everything must stay repo-agnostic, layout and config: the one seam.
taskcenter AGENTS.md
AGENTS.md instructions for xiaogezi/taskcenter, covering taskcenter agent rules, safety boundaries, required workflow and verification.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
codecrucible AGENTS.md
Instructions for block/codecrucible, covering agent instructions, quick reference and landing the plane (session completion).