agentmods.dev

START_HERE

START_HERE is an agent for coding agents from zyqzyq/Unfour. It costs 0 tokens per session (924 once invoked), scanned A, original, Apache-2.0.

A repository onboarding guide for AI coding tools working in Unfour. It tells the agent which project rules and architecture documents to read before editing files.

In plain words
What is it for?
Use it at the beginning of Unfour tasks to find global instructions, package boundaries, architecture, interface rules, testing guidance, and release requirements.
Why use it?
It helps the agent start with the correct context and follow the repository's active rules instead of relying on outdated notes.

Agent

not rated 2 3d ago A scan 0 tokens original Apache-2.0
View the source file zyqzyq/Unfour
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 agents/zyqzyq/unfour/start_here
Clone the repo
git clone --depth 1 https://github.com/zyqzyq/Unfour

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 START_HERE

README.md
[![agentmods](https://agentmods.dev/badge/agents/zyqzyq/unfour/start_here.svg)](https://agentmods.dev/agents/zyqzyq/unfour/start_here)
Your own site
<a href="https://agentmods.dev/agents/zyqzyq/unfour/start_here"><img src="https://agentmods.dev/badge/agents/zyqzyq/unfour/start_here.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 924 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00924
Opus 5 $0.00000 $0.00462
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00092

Measured 3d ago against content hash e68ca40ad3ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

START_HERE 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.

docs/agents/START_HERE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Start Here

This is the stable repository onboarding entrypoint for AI coding tools working in Unfour. Use it to choose the smallest useful context set before touching files.

Source Priority

Use these sources in order when documents overlap:

  1. Root AGENTS.md for global rules, package boundaries, command-bus expectations, verification defaults, and reporting requirements.
  2. The current user task for scope and acceptance criteria.
  3. This file for repository reading order.
  4. docs/architecture/* for durable architecture, storage, package boundary, and security model details.
  5. docs/ui/* for UI design-system and interaction rules.
  6. docs/testing/* and docs/release/* for release-readiness and verification expectations.
  7. Package or crate AGENTS.md / README.md for local ownership rules.

Historical checkpoint, progress, task, and audit files live under docs/archive/. They are useful for archaeology only and must not override the active documents above.

Read in this order, stopping when the task has enough context:

  1. AGENTS.md.
  2. docs/agents/START_HERE.md.
  3. For package boundaries or dependency direction: docs/architecture/package-boundaries.md.
  4. For repository shape or call chains: docs/architecture/project-structure.md.
  5. For persistence, credentials, activity, or workspace scope: docs/architecture/data-storage.md and docs/architecture/security-model.md.
  6. For UI, layout, component, style, or interaction changes: design.md, docs/ui/design-system.md, and docs/ui/interaction-guidelines.md.
  7. For MCP work: docs/mcp/overview.md, docs/mcp/tools.md, and docs/mcp/codex-setup.md.
  8. For release or verification work: docs/testing/release-verification.md, docs/testing/manual-test-cases.md, and docs/release/release-checklist.md.
  9. The relevant package or crate AGENTS.md / README.md, if present.
  10. Source files, only as needed to understand or change the implementation.

Read the full file on GitHub · 100 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 · 100 lines · 0 tokens per session scan A e68ca40ad3ab

Subscribe to this mod's changes

START_HERE is an agent published in the GitHub repository zyqzyq/Unfour (2 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 924 tokens. 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.

api-clientlocal-firstmcpsshtauri
Related

Other agents, from other repositories

altai-implementer

Implements one bounded ALTAI roadmap slice and its tests. Default working agent for roadmap PRs.

altaidevorg/altai-app · 27 tokens

altai-explorer

Read-only ALTAI repository exploration. Use when file ownership or existing patterns are unclear before implementing a roadmap item.

altaidevorg/altai-app · 28 tokens

altai-reviewer

Read-only diff review for a risky ALTAI PR. Reports actionable findings only.

altaidevorg/altai-app · 22 tokens

altai-test-triage

Triages failing tests/logs into product defects, flaky tests, environment problems, and pre-existing failures.

altaidevorg/altai-app · 28 tokens

Test Engineer

Writes tests first, then implementation. Strict TDD.

altaidevorg/altai-app · 14 tokens

researcher

Sample subagent that does focused research on a single question.

altaidevorg/altai-app · 15 tokens