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.
curl -O https://raw.githubusercontent.com/Cruxia-Labs/sagrada-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Cruxia-Labs/sagrada-mcpWrote 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.
[](https://agentmods.dev/instructions/cruxia-labs/sagrada-mcp/agents-md)<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.
<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>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 | $0.00465 | $0.00465 |
| Opus 5 | $0.00233 | $0.00233 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
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.
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 onmcpis 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.
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.
- 9d ago First seen · 29 lines · 465 tokens per session scan A 6ea30883a0ec
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.
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.
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.
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).
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).
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.
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.