Borrowing it
Nothing to install: this file belongs to gosuda/portal-tunnel. 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/gosuda/portal-tunnel/main/AGENTS.mdgit clone --depth 1 https://github.com/gosuda/portal-tunnelWrote 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/gosuda/portal-tunnel/agents-md)<a href="https://agentmods.dev/instructions/gosuda/portal-tunnel/agents-md"><img src="https://agentmods.dev/badge/instructions/gosuda/portal-tunnel/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/gosuda/portal-tunnel/agents-md"><img src="https://agentmods.dev/badge/instructions/gosuda/portal-tunnel/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 | $0.00861 | $0.00861 |
| Opus 5.5 | $0.00344 | $0.00344 |
| Sonnet 5.5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
portal-tunnel 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 23d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Keep this file short and behavioral. Architecture documentation should primarily describe the current architecture. Issues and pull requests preserve short-lived refactoring, migration, and rejected-design history.
Development Principles
- Minimize concepts, duplication, and ceremony.
- Do not keep historical artifacts that no longer explain or protect current behavior.
- Prefer a single stable contract with one real owner.
- Prefer local simplicity over premature or speculative abstraction.
- Add indirection only when it removes real coupling or protects a real boundary.
- Before introducing a new mechanism or local subsystem, judge whether the problem is large, repeated, long-lived, or independent enough to justify one. Examples include interfaces, wrappers, helpers, callbacks, hooks, locks, channels, goroutines, registries, caches, shadow state, generation counters, configuration knobs, feature flags, state machines, reconciliation loops, adapters, and extension points. Prefer the existing owner, control flow, data flow, lifecycle, or serialization when they already express the requirement clearly; introduce a new mechanism when the problem itself warrants a durable new concept.
- Do not generalize a one-off problem by default. Generalize when multiple real callers, implementations, lifecycle paths, or an enduring boundary make the broader form useful on its own.
- Tests protect stable public behavior, protocol and security invariants, and real lifecycle E2E behavior.
- Keep a regression test when the regression reveals a contract or invariant that remains important.
- Do not test incidental implementation details such as call sequence, log output, retry count, or file metadata unless they are themselves part of a stable contract.
- When a refactor makes an implementation-coupled test obsolete, delete it if no enduring behavior or invariant would be left unprotected.
- Prefer deterministic unit tests at the lowest coherent owner, or real black-box E2E tests in
e2e/; do not add middle-layer tests that assemble several subsystems with fake transports or callbacks to inspect internal state. - Never add a production callback, interface, config knob, wrapper, synchronization primitive, or injection seam only to make a test possible.
- When a regression crosses components, protect the enduring invariant in its lowest owner; otherwise assert the real behavior in
e2e/.
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.
- 23d ago Changed · +4 lines · +221 tokens per session 301cbddac91e
- 1mo ago Changed · +3 lines · +99 tokens per session 2d9eb35dc242
- 1mo ago Changed · +9 lines · +160 tokens per session ef01198eebaa
- 1mo ago First seen · 34 lines · 381 tokens per session scan A 5d5e7ff3825f
portal-tunnel AGENTS.md is an instructions file published in the GitHub repository gosuda/portal-tunnel (291 stars, last pushed yesterday), licensed MIT. It adds 861 tokens to every session, about $0.0034 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.