What is loom AGENTS.md?

Repository instructions for Loom, a project with Rust services, Python search algorithms, tests, and adapters for several coding agents.

Use them when editing Loom's Rust or Python code, agent adapters, deployment logic, documentation, or integration tests.

They show developers where each part belongs and which commands check builds, formatting, and tests.

How valkor-ai/loom configures Codex and OpenCode

About the project

Loom is a delivery harness that guides coding agents through defining, planning, implementing, checking, repairing, previewing, and handing off software changes. It is used with Claude Code, Codex, OpenCode, and other coding agents when work must be continued or inspected across sessions. The catalogue skills, hooks, commands, instructions, and plugin extend or operate this workflow.

valkor-ai/loom · 1,415 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to valkor-ai/loom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/valkor-ai/loom/main/AGENTS.md

Clone the repo

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

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/valkor-ai/loom/agents-md/github.svg)](https://agentmods.dev/instructions/valkor-ai/loom/agents-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/valkor-ai/loom/agents-md"><img src="https://agentmods.dev/badge/instructions/valkor-ai/loom/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 736 This file is loaded in full into every session.

When invoked 736 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00736	$0.00736
Opus 5.5	$0.00294	$0.00294
Sonnet 5.5	$0.00147	$0.00147
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash 30cfbeeba5a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loom 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 2mo 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

src/rust/: workspace crates. mcp-server exposes tools; domain crates such as planning, execution, deploy, and knowledge own workflow behavior; contracts, core, and state provide shared protocols.
src/python/algorithms/: bundled BM25, TF-IDF, tokenization, and worker code.
tests/rust/ and tests/python/algorithms/: integration and algorithm tests, organized by product domain.
plugins/{codex,claude-code,opencode}/: agent adapters. Shared Loom and deploy guidance lives under plugins/shared/; avoid duplicating shared rules in adapter files.
docs/, assets/, and scripts/: user documentation, README media, and local install helpers.

Build, Test, and Development Commands

Run commands from the repository root:

npm run rust:test
npm run python:test
cargo fmt --manifest-path src/rust/Cargo.toml --all --check
cargo build --manifest-path src/rust/Cargo.toml -p mcp-server -p setup

Use targeted Rust tests while iterating, for example:

cargo test --manifest-path src/rust/Cargo.toml -p deploy --test deploy_workflow

Refresh a local integration after runtime or plugin changes with ./install.sh --agent codex --local-build; Claude Code and OpenCode helpers are in scripts/.

Coding Style & Naming Conventions

Use Rust 2021 conventions and keep code rustfmt-clean. Name modules, functions, and files with snake_case; types and traits with UpperCamelCase; constants with SCREAMING_SNAKE_CASE. Python follows four-space indentation, snake_case, and test_*.py naming. Keep changes within existing domain boundaries and prefer structured Serde models over ad hoc JSON manipulation.

Testing Guidelines

Add focused regression coverage for behavioral changes. Rust integration tests belong in the matching tests/rust/<domain>/ suite; local unit tests may remain beside implementation code. Python tests use pytest. Run the affected package or test target first, then both product test lanes before release-impacting changes. Fixes should reproduce the prior failure.

Read the full file on GitHub · 54 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.

2mo ago First seen · 54 lines · 736 tokens per session scan A 30cfbeeba5a5

Subscribe to this mod's changes

loom AGENTS.md is an instructions file published in the GitHub repository valkor-ai/loom (1,415 stars, last pushed 3d ago), licensed Apache-2.0. It adds 736 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

loom AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
loom AGENTS.mdvalkor-ai/loom	Instructions file	1.4k	3d ago	Apache-2.0	A	736	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

loom: Instructions file for Codex