Borrowing it
Nothing to install: this file belongs to fiberfx/mercury. 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/fiberfx/mercury/master/AGENTS.mdgit clone --depth 1 https://github.com/fiberfx/mercuryWrote 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/fiberfx/mercury/agents-md)<a href="https://agentmods.dev/instructions/fiberfx/mercury/agents-md"><img src="https://agentmods.dev/badge/instructions/fiberfx/mercury/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/fiberfx/mercury/agents-md"><img src="https://agentmods.dev/badge/instructions/fiberfx/mercury/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 | $0.00545 | $0.00545 |
| Opus 5.5 | $0.00218 | $0.00218 |
| Sonnet 5.5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
mercury 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 5d 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in the Mercury distribution repository
This repository owns consumer bootstrap tools, documentation distribution and release packaging. It is not the complete Mercury module source workspace. Inspect the files that exist before proposing a package build; do not assume ui/, core/, hyperscript/, mx/ or an upstream monorepo is available here.
Preserve other writers' changes and the user's existing application. For page creation, read agents/SKILL.md from the extracted bundle and choose the route that fits the task: existing tools, browser-only HTML or supported native mx. Browser JavaScript is required for interactive pages; Phoenix/BEAM is optional. npm is an optional distribution mechanism, not a prerequisite for the Python bootstrap or native CLI runtime.
Distribution invariants
- The caller supplies both a versioned manifest URL and a reviewed SHA-256. Verify the manifest bytes before parsing them. A manifest and checksum from the same untrusted location do not create an independent trust anchor.
schema_version: 1identifiesassets.bundleandassets.native_linux_x64, each withfile,urlandsha256. Verify downloaded asset bytes before extracting or executing them. Keep extraction inside the selected destination; do not weaken failure handling to make a release pass.- Preserve dependency pins, native provenance and license notices. Report the source revision, asset hashes and checks actually performed without substituting a planned tag for an observed release.
- Native candidates require Linux x64, glibc 2.39 or later and
libgcc_s.so.1; they were tested on glibc 2.41. Do not claim support for musl, other architectures, macOS or Windows based on that evidence.--docs-onlyis the documentation route on other hosts. - Keep publication state explicit. Source-side tests, local packages, public asset downloads and digest-pinned image pulls are separate evidence. Never invent a hash, published version, successful browser interaction or release URL.
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.
- 5d ago First seen · 20 lines · 545 tokens per session scan A 4a00f8dcbf61
mercury AGENTS.md is an instructions file published in the GitHub repository fiberfx/mercury (44 stars, last pushed 12d ago), licensed MIT. It adds 545 tokens to every session, about $0.0022 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 2026-11-15.
mercury AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mercury AGENTS.mdfiberfx/mercury | Instructions file | 44 | 12d ago | MIT | A | 545 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,887 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,772 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 285k | 2d ago | MIT | A | 4,342 | Codex, OpenCode |