What is jido_ai AGENTS.md?

A project guide for Jido.AI, an Elixir toolkit for building AI agents that use tools and explicit strategies. It describes the runtime, commands, architecture, model-provider integration, policies, and testing standards.

Use it when developing or maintaining Jido.AI agents, running tests and quality checks, choosing agent strategies, integrating language-model providers, and documenting the project.

It gives developers a shared baseline for configuring models, timeouts, retries, tool rules, structured data, errors, and provider-specific behavior.

How agentjido/jido_ai configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to agentjido/jido_ai. 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/agentjido/jido_ai/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/agentjido/jido_ai

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/agentjido/jido_ai/agents-md/github.svg)](https://agentmods.dev/instructions/agentjido/jido_ai/agents-md)

Your own site

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

Per session 462 This file is loaded in full into every session.

When invoked 462 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	$0.00462	$0.00462
Opus 5.5	$0.00185	$0.00185
Sonnet 5.5	$0.00092	$0.00092
Haiku 4.5	$0.00046	$0.00046

Measured 2mo ago against content hash 22db4d39a498, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jido_ai 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 · 46 lines

What it actually says

AGENTS.md - Jido.AI Guide

Intent

Build tool-using AI agents with explicit strategy, runtime policy, and reliable request orchestration.

Runtime Baseline

Elixir ~> 1.18
OTP 27+ (release QA baseline)

Commands

mix test (default alias excludes :flaky)
mix test.fast (stable smoke suite)
mix precommit (format, compile --warnings-as-errors, doctor --summary --raise, test.fast)
mix q or mix quality (format, compile, credo, doctor, dialyzer)
mix docs

Architecture Snapshot

Jido.AI.Agent + strategy agents (CoD, CoT, AoT, ToT, GoT, TRM, Adaptive)
Jido.AI.Actions.*: reusable runtime actions for chat/tool/structured flows
ReqLLM integration for provider abstraction and model routing
Policy/observability modules for retries, quotas, telemetry, and traceability

Standards

Keep model selection, timeout, retry, and tool policy explicit
Use Zoi-first schemas for tool inputs and structured outputs
Keep provider-specific behavior behind ReqLLM integration boundaries
Preserve tagged tuple and structured error contracts
Prefer deterministic fallback behavior over ad-hoc prompt pipelines

Testing and QA

Cover strategy behavior, tool-call loops, and error/fallback handling
Keep flaky tests isolated behind tags; maintain a stable smoke subset (mix test.fast)
Validate public examples/scripts when runtime behavior changes

Release Hygiene

Keep semver ranges stable (~> 2.0 ecosystem peers; package currently 2.0.0-rc.0)
Use Conventional Commits
Do not modify CHANGELOG.md; release notes are generated from Git history during release, so keep changes focused on proper Conventional Commits.
Update guides and migration notes for behavior/API changes

References

README.md
usage-rules.md
guides/
https://hexdocs.pm/jido_ai

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 · 46 lines · 462 tokens per session scan A 22db4d39a498

Subscribe to this mod's changes

jido_ai AGENTS.md is an instructions file published in the GitHub repository agentjido/jido_ai (211 stars, last pushed today), licensed Apache-2.0. It adds 462 tokens to every session, about $0.0018 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.

Building agents LLM ai ai-agents elixir elixir-package jido

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

jido_ai: Instructions file for Codex