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.
curl -O https://raw.githubusercontent.com/Hardik-Singh/invariance-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Hardik-Singh/invariance-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/hardik-singh/invariance-mcp/agents-md)<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.
<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>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 | $0.01711 | $0.01711 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
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 8d 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.
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 a403. 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;_forkwrites).
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.
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.
- 8d ago First seen · 96 lines · 1,711 tokens per session scan A 1f0cfadfe386
invariance-mcp AGENTS.md is an instructions file published in the GitHub repository Hardik-Singh/invariance-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,711 tokens to every session, about $0.0086 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.
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.