Borrowing it
Nothing to install: this file belongs to whisper-sec/whisper-cli. 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/whisper-sec/whisper-cli/main/AGENTS.mdgit clone --depth 1 https://github.com/whisper-sec/whisper-cliWrote 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/whisper-sec/whisper-cli/agents-md)<a href="https://agentmods.dev/instructions/whisper-sec/whisper-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/whisper-sec/whisper-cli/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/whisper-sec/whisper-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/whisper-sec/whisper-cli/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 | $0.01021 | $0.01021 |
| Opus 5 | $0.00511 | $0.00511 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
whisper-cli 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repository. Humans want CONTRIBUTING.md, which this does not replace: everything there still applies, and this file adds what an agent needs that a human would infer.
The one-line summary
whisper is a single static Go binary: the command-line client for Whisper. It gives an
agent a real, routable IPv6 /128 on AS219419, wires egress so traffic sources from that
address, and verifies the result end to end against public DNSSEC, DANE and RDAP.
Build and test
Requires Go 1.25+. Run all four before proposing a change; CI runs the same set and a failure in any one of them is a failure.
go build ./... # everything compiles
go vet ./... # no vet findings
go test ./... # all tests pass
gofmt -l . # MUST print nothing; if it lists a file, run gofmt -w on it
Run the binary from source with go run ./cmd/whisper --help. Cross-compiling every
shipped platform is ./build-all.sh, driven by platforms.txt.
Layout
cmd/whisper the entry point, thin
internal/cli one file per command, Cobra wiring and the TUI
internal/... the client core: config, transport, identity, verification
skills/ SKILL.md files describing what the tool can do, for agent runtimes
scripts/ install.sh and install.ps1, the published installers
A new command is a file under internal/cli, registered with the root command. Keep the
command file small and put real logic in a sibling package so it can be tested without a
terminal.
Invariants, and why
These are not style preferences. Breaking one breaks the product.
- Be conservative in what you emit, liberal in what you accept. Accept the form a user would naturally reach for (an address with or without brackets, a name with or without a trailing dot, a flag or a positional). Emit something strict and predictable.
- An error is one clear sentence that says what to do next, never a stack trace and never an opaque code. If a command needs a key, say so and say how to get one.
- The keyless half must stay keyless. A large part of this tool works with no account: verification, RDAP, encryption to an agent's DANE-discovered key, public graph reads. Do not add a key check to a path that does not need one, and never let a keyless path fall back to some ambient credential.
- Never print, log, or embed a credential. Not a key, not a token, not in a debug branch, not in a test fixture that looks real. Tests use obvious placeholders.
- CGO stays disabled and the binary stays static. A new third-party dependency has to earn its place; prefer the standard library.
- Tests are self-contained. No live network and no external service, ever. Use an in-process server and fixtures. A test that reaches the internet is a flaky test and a CI outage waiting to happen.
- Every Go file carries the SPDX header:
// SPDX-License-Identifier: MIT // Copyright (c) 2026 viaGraph B.V. (Whisper Security)
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 · 87 lines · 1,021 tokens per session scan A 1f50dccdf7bf
whisper-cli AGENTS.md is an instructions file published in the GitHub repository whisper-sec/whisper-cli (2 stars, last pushed yesterday), licensed MIT. It adds 1,021 tokens to every session, about $0.0051 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 2026-09-18.
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).
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.
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.
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).