Borrowing it
Nothing to install: this file belongs to vadim-filimonov/openrater. 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/vadim-filimonov/openrater/main/AGENTS.mdgit clone --depth 1 https://github.com/vadim-filimonov/openraterWrote 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/vadim-filimonov/openrater/agents-md)<a href="https://agentmods.dev/instructions/vadim-filimonov/openrater/agents-md"><img src="https://agentmods.dev/badge/instructions/vadim-filimonov/openrater/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/vadim-filimonov/openrater/agents-md"><img src="https://agentmods.dev/badge/instructions/vadim-filimonov/openrater/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 | $0.00796 | $0.00796 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
openrater 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenRater — agent guide
OpenRater turns rate filings and rating manuals into executable, auditable rating engines. The division of labor is absolute: the AI transcribes; the deterministic platform validates, builds, and rates. Nothing probabilistic executes at rating time.
The loop
filing PDF ──(you transcribe, following the spec)──▶ workbook (.xlsx)
──(validate_workbook: R-### rules, zero AI)──▶ fix cells, repeat
──(build_plan_from_workbook)──▶ plan + build report (citations, gaps, vectors)
──(quote_risk / rerate_book)──▶ premiums with traces
Connect the MCP server
# dev (this repo; server on :8001):
claude mcp add openrater -- npx tsx services/mcp/src/main.ts
# env: RATER_API_URL (default http://127.0.0.1:8001) · RATER_APP_URL · RATER_API_KEY
Tools: get_transcription_spec (sectioned — no argument returns the
table of contents) · get_workbook_template ·
get_capability_registry · list_plans · get_plan ·
get_plan_input_schema · validate_workbook ·
build_plan_from_workbook · get_build_report ·
export_plan_workbook (build or current state) · reingest_diff ·
apply_reingest · quote_risk · rerate_book · compare_plans
(what changed between two plans, with an Exhibits deep link) ·
compare_runs (same book through two runs: totals, movers, newly
refused rows) · open_in_openrater · runtime_status (the doctor —
health, next actions, and sample: the seeded reference plan +
bundled sample filing/demo-book paths).
Rules you must follow
- Review stops. Do not proceed past (a) a completed workbook,
(b) a failed check, (c) the
gaps_and_assumptionssheet, or (d) a failedtest_casesvector without showing the human the artifact and asking. Share theopen_in_openraterlink at every stop. - Bulk data stays out of the chat. Books travel as file paths; report counts and summaries, never row dumps.
- Never work around a refusal. R-### errors and "not supported" messages are the platform speaking precisely; fix the workbook or record the gap — don't approximate.
- You fetch documents; never automate SERFF. The user supplies the filing PDF themselves.
- Filed rates govern. Outputs are reconstructions; tell the user
to verify against the filing's own worked examples (
test_cases).
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 · 64 lines · 796 tokens per session scan A 805b52e74aaf
openrater AGENTS.md is an instructions file published in the GitHub repository vadim-filimonov/openrater (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 796 tokens to every session, about $0.0040 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.