What is shep AGENTS.md?

Instructions for Shep, a command-line platform that uses AI to gather requirements, create plans, and carry out software work. Its workflow requires each feature to begin with a specification, stored as editable YAML files.

Use them when starting a feature, editing specifications, working across the platform’s architecture layers, or running unit, integration, end-to-end, and validation checks.

They provide the required planning process and the commands for building, testing, formatting, and validating the project.

shep AGENTS.md — Instructions file for Codex and OpenCode by shep-ai: Instructions for Shep, a command-line platform that uses AI…

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/shep-ai/shep/agents-md

Clone the repo

git clone --depth 1 https://github.com/shep-ai/shep

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/shep-ai/shep/agents-md.svg)](https://agentmods.dev/instructions/shep-ai/shep/agents-md)

Your own site

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

Per session 1,927 This file is loaded in full into every session.

When invoked 1,927 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	$0.01927	$0.01927
Opus 5	$0.00963	$0.00963
Sonnet 5	$0.00385	$0.00385
Haiku 4.5	$0.00193	$0.00193

Measured 4d ago against content hash 8c07bacc57ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shep 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 · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Cursor, Windsurf, Copilot, etc.) working in this repository.

Project

@shepai/cli — Autonomous AI Native SDLC Platform. Users run shep in a repo to gather requirements via AI, generate plans, and execute implementation autonomously.

Spec Workflow

All feature work MUST begin with a spec. See spec-driven-workflow.

Specs live in specs/NNN-feature-name/. Edit YAML only — Markdown is auto-generated.

Commands

Command	Purpose
`pnpm build`	Build CLI + web
`pnpm test`	Run all tests
`pnpm test:unit`	Unit tests only
`pnpm test:int`	Integration tests only
`pnpm test:e2e`	Playwright e2e tests
`pnpm lint:fix`	Fix lint issues
`pnpm validate`	Lint + format + typecheck + tsp
`pnpm dev:cli`	Run CLI locally (ts-node)
`pnpm dev:web`	Start Next.js dev server

Architecture

Clean Architecture — four layers in packages/core/src/ (dependencies point inward):

domain/ — Core business logic, no external deps
application/ — Use cases, output port interfaces
infrastructure/ — External concerns: DB, agents, services
presentation/ — CLI, TUI, Web UI (src/presentation/)

See clean-architecture.

Mandatory Rules

MANDATORY — TDD: Write failing tests FIRST (RED → GREEN → REFACTOR). Every plan phase must define explicit TDD cycles. See tdd-guide.
MANDATORY — TypeSpec-first: Domain models defined in tsp/. Run pnpm tsp:compile to generate packages/core/src/domain/generated/output.ts. Never edit generated files. See typespec-guide.
MANDATORY — Agent resolution: No component may hardcode an agent type. All resolution flows through IAgentExecutorProvider. See agent-system. The supervisor agent (spec 093) follows the same rule — its evaluator LLM is resolved through IAgentExecutorProvider, never a hardcoded provider SDK.
MANDATORY — Storybook stories: Every web UI component MUST have a colocated .stories.tsx file. Commits without stories will be rejected.
MANDATORY — Spec-driven: All features start with a spec. No implementation without a spec.
MANDATORY — Actor namespaces: When an agent acts on a user's behalf (e.g., the supervisor closing an approval gate), it MUST use the supervisor:<id> actor namespace. The user namespace user:<id> always wins on conflict — ApproveAgentRunUseCase / RejectAgentRunUseCase enforce this invariant. See supervision.

Read the full file on GitHub · 139 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.

4d ago First seen · 139 lines · 1,927 tokens per session scan A 8c07bacc57ae

Subscribe to this mod's changes

shep AGENTS.md is an instructions file published in the GitHub repository shep-ai/shep (247 stars, last pushed today), licensed MIT. It adds 1,927 tokens to every session, about $0.0096 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.

Planning Productivity agentic-ai ai-agents ai-code-generation ai-native claude-code cursor

markplane CLAUDE.md

Instructions for zerowand01/markplane, covering claude.md, project overview, build & test, workspace structure and key conventions.

zerowand01/markplane · 826 tokens

pyobfus CLAUDE.md

Instructions for zhurong2020/pyobfus, covering pyobfus 开发约定, ⚡ current pending work (cold-start 必读), ⏳ 2026-08-30 — 客户 paid-invoice pdf 已升级 stripe 工程处理, ✅ 2026-08-24 — 0.5.17 / mcp 0.3.8 发布与外部渠道收尾 and ✅ 2026-08-21 — 周期性复查（下载量 + glama + claude plugin），全部无变化.

zhurong2020/pyobfus · 20,508 tokens

shep AGENTS.md