sagrada-mcp: Instructions file for Codex

AGENTS.md

sagrada-mcp AGENTS.md is an instructions file for Codex, OpenCode from Cruxia-Labs/sagrada-mcp. It costs 465 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for developers working on sagrada-mcp, an MCP server that tracks and verifies reasoning state for AI systems.

In plain words
What is it for?
Use them when modifying the server, updating vendored packages, running its tests, or checking that verdict records can be verified offline.
Why use it?
They document required Python versions, dependency limits, vendored-code rules, tests, deterministic checks, and verification receipts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is Cruxia-Labs/sagrada-mcp's own configuration. It tells Codex and OpenCode how to work on sagrada-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sagrada-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Cruxia-Labs/sagrada-mcp. 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/Cruxia-Labs/sagrada-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Cruxia-Labs/sagrada-mcp

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 sagrada-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cruxia-labs/sagrada-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/cruxia-labs/sagrada-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cruxia-labs/sagrada-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cruxia-labs/sagrada-mcp/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.

agentmods 80×15 button for sagrada-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cruxia-labs/sagrada-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cruxia-labs/sagrada-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 465 This file is loaded in full into every session.
When invoked 465 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00465 $0.00465
Opus 5 $0.00233 $0.00233
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured 9d ago against content hash 6ea30883a0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sagrada-mcp 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 9d 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 · 29 lines

What it actually says

AGENTS.md

Conventions for working in sagrada-mcp — for the AI agents (and humans) who develop it. This file is itself a structured rule set, so our own published linter scans it on every push: we run the determinism we sell. See .github/workflows/dogfood.yml.

Rules

  • runtime: Python 3.10+
  • dependencies: mcp>=1.0.0,<2.0.0, sagrada-engine, cryptography — the upper bound on mcp is load-bearing, not caution
  • vendoring: sagrada_mcp/_vendor/ holds copies of not-yet-published packages; the server imports the real package first and falls back to the copy
  • vendor-edits: never patch a vendored file in place — change it upstream and re-vendor, or the copy silently forks
  • testing: the suite runs against whichever copy the server bound, never a different one (tests/conftest.py)
  • determinism: the preflight gate is deterministic and engine-free — refusal never depends on the compiled wheel
  • receipts: every gate verdict emits an ER1 receipt that recomputes offline with uvx er1-verify
  • scope: coherence, not correctness — a receipt certifies that a verdict follows from the recorded inputs, never that an input is true
  • recognition: the gate maps actions by a finite vocabulary; an unrecognised action is not mapped, and an unmapped action is ALLOWed
  • format-naming: ER1 is an "open format", not a "standard" — that word is earned only when a second party recomputes the vectors
  • attribution: commits are authored as Mars Ausili [email protected]
  • licensing: code is Apache-2.0

What the linter anchors on

  • key: value — a structured rule (like every line above)
  • - term — definition — a bullet with an em-dash
  • A bold label at the start of a line

Free prose with no structured shape is never guessed at — that is the deterministic floor, by design.

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. 9d ago First seen · 29 lines · 465 tokens per session scan A 6ea30883a0ec

Subscribe to this mod's changes

sagrada-mcp AGENTS.md is an instructions file published in the GitHub repository Cruxia-Labs/sagrada-mcp (0 stars, last pushed 21d ago), licensed Apache-2.0. It adds 465 tokens to every session, about $0.0023 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 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 · 5,153 tokens

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

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 · 3,735 tokens