What is forge AGENTS.md?

Repository guidance for coding agents working on Forge, a Rust program that provides a terminal-based AI coding assistant. It explains the project structure, development rules, checks, and Git workflow.

Use it when changing Forge code, understanding its crates, running checks, or following its feature-branch and pull-request process.

It gives an agent the project context and rules needed to make changes consistently and safely. It also clarifies how to validate work before submitting it.

forge AGENTS.md — Instructions file by NorviaLabs

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/norvialabs/forge/agents-md

Clone the repo

git clone --depth 1 https://github.com/NorviaLabs/forge

Made for: Codex, OpenCode.

Per session 836 This file is loaded in full into every session.

When invoked 836 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	$0.00836	$0.00836
Opus 5	$0.00418	$0.00418
Sonnet 5	$0.00167	$0.00167
Haiku 4.5	$0.00084	$0.00084

Measured 2d ago against content hash 7f5df45ec0a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge 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 2d 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working in this repository.

Project Overview

Forge is a Rust workspace for a terminal AI coding-agent harness. The main binary launches a full-screen TUI and lives in crates/forge-cli.

Key crates:

crates/forge-cli: CLI entrypoint and startup wiring.
crates/forge-tui: Ratatui terminal UI, overlays, commands, model picker, chat loop UI.
crates/forge-core: Agent loop, message/session lifecycle, tool execution orchestration.
crates/forge-model: Native provider transports and wire-format normalization.
crates/forge-connect: Provider profiles, credential store, model catalog, /connect support.
crates/forge-tools: Built-in tools and validation. Includes update_plan (model-callable checklist; emits a plan_update turn event; no persisted plan state) and ask_user_question (pauses the turn on WaitReason::Question until the user answers).
crates/forge-mcp: MCP client and remote tool registration.
crates/forge-config: Config loading and model/provider migration.
docs/: User/design documentation.

Development Rules

Never commit directly to main. Do all work on a feature branch and open a PR (see Git Workflow).
Keep changes focused; avoid unrelated refactors, dependency updates, or formatting churn.
Prefer small root-cause fixes over call-site patches.
Match existing Rust style and crate-local patterns.
For any TUI, visual, navigation-hint, focus-presentation, or design-system change, read FORGE-DESIGN.md first and follow its visual language, focus invariants, palette, terminology, and displayed-binding rules.
Always run relevant tests for the code you change before handoff.
Add or update tests for behavior changes, and implement new test cases when changes are significant.
Update docs when commands, configuration, provider behavior, architecture, or safety behavior changes.
Never commit API keys, OAuth tokens, credentials, .forge/ runtime data, or proprietary fixtures.

Read the full file on GitHub · 84 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.

2d ago First seen · 84 lines · 836 tokens per session scan A 7f5df45ec0a2

Subscribe to this mod's changes

forge AGENTS.md is an instructions file published in the GitHub repository NorviaLabs/forge (5 stars, last pushed 2d ago), licensed MIT. It adds 836 tokens to every session, about $0.0042 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.

Data and AI Git and workflow LLM Languages ai-coding-assistant cli code-editor coding-agent developer-tools

forge AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Project Overview

Development Rules

What this file has done since we first saw it

Other instructions, from other repositories

Albatross AGENTS.md

Xenon CLAUDE.md

ankaloop AGENTS.md

little-coder AGENTS.md

evoflux AGENTS.md

vix AGENTS.md