Borrowing it
Nothing to install: this file belongs to alexfrmn/murmur. 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/alexfrmn/murmur/main/AGENTS.mdgit clone --depth 1 https://github.com/alexfrmn/murmurWrote 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/alexfrmn/murmur/agents-md)<a href="https://agentmods.dev/instructions/alexfrmn/murmur/agents-md"><img src="https://agentmods.dev/badge/instructions/alexfrmn/murmur/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/alexfrmn/murmur/agents-md"><img src="https://agentmods.dev/badge/instructions/alexfrmn/murmur/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 | $0.00810 | $0.00810 |
| Opus 5.5 | $0.00324 | $0.00324 |
| Sonnet 5.5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
murmur 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 26d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Murmur
Read CONTRIBUTING.md and the affected package documentation before changing code. Keep fixes in a focused branch or worktree from current main; do not overwrite unrelated work. Commit only the intended files. Merge after the designated reviewer approves the exact head and its required checks pass. A changed head needs a new review of the change, including conflict resolution. Preserve both intended sides of a conflict.
Shared behavior
packages/setupowns onboarding, selected profile paths, service/client configuration and update checks. Desktop and terminal integrations consume its CLI contracts; do not add independent profile discovery, version comparison or configuration writers.- Do not silently canonicalize a selected profile path used to derive the default service name: aliases can name the same files while selecting different services.
package.jsonengines.nodeowns the runtime minimum. Use the shared capability check before loading the engine; keep stated requirements covered byscripts/check-node-requirements.mjs.contracts/setup/v1/fixturesis the shared setup contract corpus. JavaScript, Swift and Go read the same files. Change a frozen contract deliberately across consumers; do not silently rename codes or copy fixtures into another implementation.- Preserve the difference between configured and observed state, transport delivery and agent wake, and unknown and healthy. A successful command response does not by itself prove a running daemon or a returned reply.
- User-facing integrations default to English and retain Russian as an explicit choice. Keep protocol codes, command arguments and paths stable; translate presentation through the integration's localization resources.
Safety and ownership
- Use disposable profiles and isolated local brokers for tests. Never restart a shared broker, mutate an existing user's identity or client settings, or deploy to production without authorization for that action.
- Validate paths, profile identity and resource ownership before mutation. Test refusal by inspecting unchanged state, not just an exit code. Do not overwrite an occupied output or install over a service you do not own.
- Never print or commit private profile configuration, invite credentials, tokens or real message contents. Fixtures use generated disposable keys and synthetic messages. Review tracked files and release contents, including accidentally added binaries and backups.
- Preserve existing user settings, especially custom status lines. Optional integrations must be explicit and reversible. Reading an inbox and marking it read are different operations.
- Unsigned release assets require clear first-open instructions. Opening a verified release-page destination does not verify the downloaded binary. Do not install updates silently.
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.
- 26d ago First seen · 35 lines · 810 tokens per session scan A b979dd48cd59
murmur AGENTS.md is an instructions file published in the GitHub repository alexfrmn/murmur (19 stars, last pushed yesterday), licensed MIT. It adds 810 tokens to every session, about $0.0032 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 2026-09-21.
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.
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.
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).