What is dotcontext AGENTS.md?

Repository instructions for dotcontext, a project that provides one runtime through a command-line interface, an agent harness, an MCP connection, and integrations with host tools. It explains the intended role of each part and where changes belong.

Use it when changing dotcontext’s command-line interface, reusable runtime, MCP request handling, or integrations with tools such as Claude Code, Codex CLI, and Pi.

It helps coding agents understand the project structure and avoid putting logic in the wrong layer. It also points them to the repository references and expected validation steps.

How vinilana/dotcontext configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to vinilana/dotcontext. 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/vinilana/dotcontext/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/vinilana/dotcontext

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/vinilana/dotcontext/agents-md/github.svg)](https://agentmods.dev/instructions/vinilana/dotcontext/agents-md)

Your own site

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

Per session 555 This file is loaded in full into every session.

When invoked 555 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	$0.00555	$0.00555
Opus 5.5	$0.00222	$0.00222
Sonnet 5.5	$0.00111	$0.00111
Haiku 4.5	$0.00056	$0.00056

Measured 2mo ago against content hash 49bc426d9ba4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dotcontext 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dotcontext Agent Instructions

This repository exposes one runtime through four surfaces:

cli -> harness <- mcp
              <- integrations (host hooks / extensions)

Agents working in this repo should preserve that separation.

Architectural Intent

cli is the operator interface
harness is the reusable execution runtime
mcp is the transport adapter for AI tools
integrations is the host hook and extension layer (Claude Code, Codex CLI, Pi)

If a change affects reusable execution logic, prefer src/harness/application. If a change affects reusable domain rules, prefer src/harness/domain. If a change affects protocol shape or request handling, prefer src/mcp/gateway. If a change affects user-facing commands or installation flows, prefer src/cli. If a change affects host event mapping or hook templates, prefer src/integrations. Do not add new code under src/services; that directory is not part of the target architecture.

Repository References

README.md explains what dotcontext is and why it exists
dotcontext.dev (source in docs/) explains how to use it
ARCHITECTURE.md explains how the harness works
CONTRIBUTING.md explains contributor workflow
CHANGELOG.md tracks release-facing changes

Expected Validation

For code changes:

npm run build
npm test -- --runInBand

For packaging or release-surface changes:

npm run build:packages
npm run smoke:packages

MCP Install Changes

If you touch mcp:install, keep these aligned:

src/cli/services/mcpInstallService.ts
src/cli/services/mcpInstallService.test.ts
README.md
docs/src/content/docs/ (published at dotcontext.dev)
CHANGELOG.md

Documentation must reflect the actual config written by the installer.

Hook Install Changes

If you touch hook install, keep these aligned:

src/cli/services/hookInstallService.ts
src/cli/services/hookDispatchService.ts
src/cli/services/__tests__/hookInstallService.test.ts
src/integrations/claude-code/, src/integrations/codex/, src/integrations/pi-dev/
README.md
docs/src/content/docs/ (installation and hooks guides)
CHANGELOG.md

Read the full file on GitHub · 75 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 · 75 lines · 555 tokens per session scan A 49bc426d9ba4

Subscribe to this mod's changes

dotcontext AGENTS.md is an instructions file published in the GitHub repository vinilana/dotcontext (576 stars, last pushed 3mo ago), licensed MIT. It adds 555 tokens to every session, about $0.0022 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.

dotcontext AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dotcontext AGENTS.mdvinilana/dotcontext	Instructions file	576	3mo ago	MIT	A	555	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	yesterday	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

dotcontext: Instructions file for Codex