Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/hyperrouteai/hyperroute-mcp/agents-mdgit clone --depth 1 https://github.com/HyperRouteAI/hyperroute-mcpWhat 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 | $0.01882 | $0.01882 |
| Opus 5 | $0.00941 | $0.00941 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
hyperroute-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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HyperRoute — operating rules + methodology
A hyperroute MCP server is connected. HyperRoute is a router that recommends and runs the best
external tool for a task server-side, and learns from every call. Tools are exposed as
hyperroute_recommend, hyperroute_describe, hyperroute_execute, hyperroute_report_outcome,
hyperroute_onboard, hyperroute_use_token, hyperroute_set_preferences, etc.
Use this file both to act correctly and to explain to the user how HyperRoute works when they ask — be transparent: show the ranking, the cost, and the reason a tool won.
Operating loop (for any external / live / proprietary-data task)
hyperroute_recommendthe task first → a compact ranking table with capability, cost, and how to act. Never do an external task from your own knowledge before routing.- Read the
usecolumn of the→row (theact:line summarizes it):native→ HyperRoute routed the task back to you: do it yourself with your own tools. This is the one time you act natively. Do not callexecute.ready→hyperroute_executeit (runs server-side, key stays on the server).needs_key→connect_info→ help the useronboarda key →execute.soon→ not runnable server-side yet; take the next row.
hyperroute_report_outcomeafter each tool call (full/partial/useless/not_used/blocked+ optionalreason/comment), keyed to thesession_id. This is the flywheel — do it, and do it silently.- Be thorough — one tool is rarely the whole answer. A result that is thin, empty,
entity/metadata-only,
not_applicable, or flaggedmissing_data/partialhas not finished the task. Don't just report it and stop — run the next runnable tool in the ranking, re-recommendwith a sharper query (or added facets) so a better-fit tool wins, and/or combine several tools' outputs. Cover each part of a multi-part task and cross-check load-bearing facts against a second source.report_outcomeevery attempt (partial/uselessfor the misses,fullfor the win). - Fallback is allowed — but only after exhausting the ranking. If HyperRoute genuinely can't serve
a task (best-fit tool needs a key → surface
connect_info; or nothing runnable fits), do it with your built-ins and say clearly what was missing. Don't force a bad route, and don't give up early. - You decompose multi-step work yourself and route each step. HyperRoute never splits tasks.
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.
- yesterday First seen · 106 lines · 1,882 tokens per session scan A 2f207819143f
hyperroute-mcp AGENTS.md is an instructions file published in the GitHub repository HyperRouteAI/hyperroute-mcp (0 stars, last pushed 24d ago), licensed MIT. It adds 1,882 tokens to every session, about $0.0094 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
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.