Borrowing it
Nothing to install: this file belongs to xuanhieu2611/Rivet. 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/xuanhieu2611/Rivet/main/AGENTS.mdgit clone --depth 1 https://github.com/xuanhieu2611/RivetWrote 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/xuanhieu2611/rivet/agents-md)<a href="https://agentmods.dev/instructions/xuanhieu2611/rivet/agents-md"><img src="https://agentmods.dev/badge/instructions/xuanhieu2611/rivet/agents-md.svg" alt="Measured on agentmods" 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 | $0.16349 | $0.16349 |
| Opus 5 | $0.08174 | $0.08174 |
| Sonnet 5 | $0.03270 | $0.03270 |
| Haiku 4.5 | $0.01635 | $0.01635 |
Grade B, and why
Rivet AGENTS.md scanned grade B with 1 finding 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `brew install --cask docker-desktop` needs sudo to link `docker-credential-osxkeychain` into How it starts
The opening of the file, as written. The whole thing — 915 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
What Rivet is
An autonomous software engineering platform: you point it at a repository, describe a task, and it runs the whole workflow (read, plan, edit, test, review, open a PR). The interesting part is the job-execution system around the coding agent, not the code generation.
PRD.md and plan.md are at the repo root and are gitignored but present on disk. Read them
for product intent and milestone scope. docs/architecture.md describes the system as it actually
exists today and is the best starting point for any structural question.
Current state: Milestone 12 is complete. Rivet now has a static public landing page, structured
diff and validation surfaces, append-only timeline motion, deterministic capture and replay, two
graded demo repositories, and a public recording of a real issue-to-PR run. A replayed run remains
an ordinary job written through the production writers. M12 adds no table, column, job status,
event type or failure category. Acceptance runs A-H are mapped in
docs/plans/milestone-12-acceptance.md; A-D and F run in pnpm test, E is integration, G is the
Docker-backed demo-repository suite, and H is the recording published on 2026-08-22.
docs/milestone-12-guide.md is the tour.
Milestone 11 is complete. Rivet can now be watched, and it defends itself. Traces, metrics and
correlated logs flow through a Telemetry port to an OTLP collector; every durable write passes a
Redactor; every API route is guarded by a session whose coverage is a test rather than a
convention; the unauthenticated edges and the spend are rate limited and the limiter fails closed;
every prompt boundary fences untrusted text; and a startup probe refuses to boot a worker whose
control plane a sandbox container can reach. M11's entire schema footprint is one nullable text
column, jobs.trace_context - no new table, no job status, no job event type and no failure
category. Its acceptance runs are A-H, mapped to their implementations in
docs/plans/milestone-11-acceptance.md; A-F need no Docker and run in pnpm test, G is
apps/worker/tests/sandbox/network-isolation.sbx.test.ts, and H is
benchmarks/prompt-injection-bait/ plus pnpm demo:observability. docs/milestone-11-guide.md is
the tour.
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.
- 6d ago First seen · 915 lines · 16,349 tokens per session scan B 1560a9a8c700
Rivet AGENTS.md is an instructions file published in the GitHub repository xuanhieu2611/Rivet (2 stars, last pushed 6d ago), licensed MIT. It adds 16,349 tokens to every session, about $0.0817 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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).
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.
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.