agentmods.dev

otito AGENTS.md

A project instruction file for coding agents working on the Otito software project. It defines where to get project context, how to assess changes, and how to prepare review or merge information.

In plain words
What is it for?
Use it when an agent needs to understand the Otito repository, assess the impact of a change, inspect project context, or check pull-request and review readiness.
Why use it?
It reduces guesswork about the repository and helps agents follow the project's required workflow before editing files. It also records where generated evidence should be stored.

Instructions file for CodexOpenCode

1 6d ago A scan 319 tokens original MIT
View the source file BASHBOP/otito
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/bashbop/otito/agents-md
Clone the repo
git clone --depth 1 https://github.com/BASHBOP/otito

Made for: Codex, OpenCode.

Per session 319 This file is loaded in full into every session.
When invoked 319 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.

ModelPer sessionOnce invoked
Fable 5 $0.00319 $0.00319
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash acf0adfb7c84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

otito 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 yesterday.

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 · 28 lines

What it actually says

otito-first workflow

This repository is the Otito project. When Codex is working here, use Otito as the first source of truth for repository context.

  • Before planning or editing, run node src/cli.js context for the task.
  • If the scope is unclear or risk is elevated, run node src/cli.js impact before changing files.
  • If the work touches PR safety or merge readiness, run node src/cli.js pr or node src/cli.js review before giving a final answer.
  • Prefer Otito MCP tools over guessing file paths, routes, contracts, or review state from memory.
  • Do not answer repository questions from memory when Otito can inspect the repository directly.
  • Keep durable generated evidence under .otito/runs/YYYY-MM-DD/<task>/. Do not write new artifacts under .dev-context/.

MCP

Use the built-in MCP server so Codex can call Otito tools directly:

node src/cli.js mcp

For Codex Desktop, Cursor, VS Code, and other MCP hosts, follow the host config examples in docs/02-mcp-agent-workflows/README.md.

Working Style

  • Read the relevant source files after getting Otito context.
  • Keep changes scoped to the smallest owner files that actually need to move.
  • Run the repo's validation commands before finishing a task.
  • Preserve the trust-layer framing: context, tests, permissions, review, and durable evidence.
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. yesterday First seen · 28 lines · 319 tokens per session scan A acf0adfb7c84

Subscribe to this mod's changes

otito AGENTS.md is an instructions file published in the GitHub repository BASHBOP/otito (1 stars, last pushed 6d ago), licensed MIT. It adds 319 tokens to every session, about $0.0016 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.

Code reviewGit and workflowProductivityai-agentsclicode-contextcode-mapdeveloper-toolslocal-first
Related

Other instructions, from other repositories

gini-agent AGENTS.md

AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.

Open-Curiosity/gini-agent · 3,639 tokens

plur CLAUDE.md

Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.

plur-ai/plur · 4,509 tokens

barkeep AGENTS.md

Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.

iannuttall/barkeep · 1,560 tokens

blz AGENTS.md

Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.

outfitter-dev/blz · 1,615 tokens

rondoflow CLAUDE.md

Instructions for rondoflow/rondoflow, covering rondoflow, project overview, tech stack, development and setup.

rondoflow/rondoflow · 2,116 tokens

CrewClaw AGENTS.md

Instructions for staruhub/CrewClaw, covering agents.md, project, boundaries (charter, 2026-07-10), commands and employee package rules.

staruhub/CrewClaw · 762 tokens