praxia-agents AGENTS.md

praxia-agents AGENTS.md is an instructions file for Codex, OpenCode from atmosware/praxia-agents. It costs 1,771 tokens per session, scanned A, original, MIT.

A set of instructions for Praxia, an agent executor that applies approved changes, and Cognia, which produces the reports it reads. It also defines where agent descriptions live and how results are saved.

In plain words
What is it for?
Use it to find the right agent definition, connect reports to follow-up fixes, and record whether changes were applied or only suggested.
Why use it?
It gives coding agents a consistent source of instructions and prevents Praxia from changing code before a person approves the proposed work.

Instructions file for CodexOpenCode

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/atmosware/praxia-agents/agents-md
Clone the repo
git clone --depth 1 https://github.com/atmosware/praxia-agents

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.

agentmods badge for praxia-agents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atmosware/praxia-agents/agents-md.svg)](https://agentmods.dev/instructions/atmosware/praxia-agents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/atmosware/praxia-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/atmosware/praxia-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,771 This file is loaded in full into every session.
When invoked 1,771 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 $0.01771 $0.01771
Opus 5 $0.00886 $0.00886
Sonnet 5 $0.00354 $0.00354
Haiku 4.5 $0.00177 $0.00177

Measured 4d ago against content hash 401eae67c57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

praxia-agents 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 4d 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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Praxis — Agent Executer

Single source of truth: All agent definitions live in .github/agents/*.agent.md. This file is the discovery index for OpenAI Codex. Before executing any agent task, read the corresponding .github/agents/<name>.agent.md file and follow every instruction defined there.


Praxia Agent Index

Praxia agents are the action counterparts to Cognia agents. Each praxia agent reads the corresponding cognia report, proposes concrete fixes or improvements, and applies them only after explicit human approval. Without approval, nothing is changed.

Output file naming:

  • Code or files were changed → praxia/{project-name}-praxia-{agent-name}-applied.md
  • No changes made (suggestions only) → praxia/{project-name}-praxia-{agent-name}-suggestions.md
  • Exception — praxia-review always writes a single, append-only todo list at praxia/praxia-review-todos.md (read on every run; checked items are preserved across runs).
Agent Reads From Can Change Code? Domain Trigger
praxia-android cognia-android report Yes Android fixes Apply Android audit findings
praxia-arch cognia-arch report No (suggestions only) Architecture redesign Propose target architecture
praxia-backend cognia-backend report Yes Backend fixes Apply backend audit findings
praxia-frontend cognia-frontend report Yes Frontend fixes Apply frontend audit findings
praxia-ios cognia-ios report Yes iOS fixes Apply iOS audit findings
praxia-perf cognia-perf report Yes Performance fixes Apply performance bottleneck fixes
praxia-po cognia-po report No (suggestions only) Product backlog Produce refined backlog & user stories
praxia-reverse cognia-reverse report No (suggestions only) Documentation Produce formal requirements & domain docs
praxia-review cognia-review report Yes (diff-scoped) Code-review remediation Apply review findings within the changeset
praxia-sec cognia-sec report Yes Security fixes Remediate security vulnerabilities
praxia-tech cognia-tech report Yes Tech debt fixes Apply technical quality improvements
praxia-test cognia-test report Yes (test files) Test writing Write missing tests
praxia-ux cognia-ux report Yes (a11y/CSS) UX fixes & specs Apply UX fixes; produce design specs

Read the full file on GitHub · 104 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.

  1. 4d ago First seen · 104 lines · 1,771 tokens per session scan A 401eae67c57c

Subscribe to this mod's changes

praxia-agents AGENTS.md is an instructions file published in the GitHub repository atmosware/praxia-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,771 tokens to every session, about $0.0089 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.

Related

Other instructions, from other repositories

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens