invariance-mcp: Instructions file for Codex

AGENTS.md

invariance-mcp AGENTS.md is an instructions file for Codex, OpenCode from Hardik-Singh/invariance-mcp. It costs 1,711 tokens per session, scanned A, original, MIT.

Instructions for using an MCP server that connects coding agents to Invariance, an observability platform for inspecting and recording AI-system activity.

In plain words
What is it for?
Use it when an agent needs to query runs, monitors, findings, workflows, guardrails, or saved evidence in Invariance.
Why use it?
It explains what the server can access and how to set it up, including the API key that a person must provide.

Instructions file for CodexOpenCode

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

This is Hardik-Singh/invariance-mcp's own configuration. It tells Codex and OpenCode how to work on invariance-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 invariance-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hardik-singh/invariance-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hardik-singh/invariance-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,711 This file is loaded in full into every session.
When invoked 1,711 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 $0.01711 $0.01711
Opus 5.5 $0.00684 $0.00684
Sonnet 5.5 $0.00342 $0.00342
Haiku 4.5 $0.00171 $0.00171

Measured 2mo ago against content hash 1f0cfadfe386, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

invariance-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 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents (Claude Desktop, Cursor, Claude Code, and any MCP client) on the tools @invariance/mcp exposes and how to use them against the Invariance observability platform.

What this server does

@invariance/mcp is an MCP server that gives an AI client direct, structured access to Invariance: it can query runs, nodes, monitors, signals, findings, reviews, cases, workflows, divergences, guardrails, receipts, and saved views, and can record traces and evidence — all as tool calls, without leaving the conversation. Tool names follow invariance_<resource>_<action>.

Every tool carries MCP annotations (readOnlyHint, destructiveHint, openWorldHint) so you can tell inspection tools from state-changing ones without reading the prose description. For complex object arguments, tools take JSON-encoded strings which the server parses before calling the API.

Setup (one-time, human-assisted)

A human configures the server in the MCP client (Claude Desktop / Cursor / Claude Code) with an INVARIANCE_API_KEY. See README.md for client config snippets. Agents should prompt the user to do this rather than attempt it themselves.

Call invariance_doctor first when you connect — it verifies server + API + auth health before you issue other calls.

Auth model

  • Reads accept an agent or operator key.
  • Receipts writes (invariance_receipt_create, invariance_receipt_batch) require an agent API key — operator tokens get a 403. All other writes work with either key.

Tools by domain

Core trace loop

  • invariance_run_start / _get / _list / _finish / _fail / _verify — wrap a task in a run (read/write).
  • invariance_node_write / _list — record tool/LLM/decision/observation nodes (read/write).
  • invariance_run_inspect, _operational_graph, _llm_calls, _node_types, _metrics, _fork — triage views over a run (read; _fork writes).

Observability and detection

  • invariance_monitor_* — create/evaluate predicates over nodes/runs; pause/resume/executions/findings.
  • invariance_signal_* — emit/list/get/acknowledge/resolve.
  • invariance_finding_* — list/get/update (status: open | review_requested | resolved | dismissed).
  • invariance_review_* — list/get/claim/unclaim/resolve.
  • invariance_divergence_list / _get (read), invariance_divergence_update (write) — expected-vs-observed gaps; transition status to open | accepted | dismissed | converted_to_monitor.

Read the full file on GitHub · 96 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. 2mo ago First seen · 96 lines · 1,711 tokens per session scan A 1f0cfadfe386

Subscribe to this mod's changes

invariance-mcp AGENTS.md is an instructions file published in the GitHub repository Hardik-Singh/invariance-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,711 tokens to every session, about $0.0068 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 2026-08-31.

Related

invariance-mcp AGENTS.md compared with instructions from other repositories

invariance-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
invariance-mcp AGENTS.mdHardik-Singh/invariance-mcpInstructions file05mo agoMITA1,711Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode