Borrowing it
Nothing to install: this file belongs to BenchBox-dev/BenchBox. 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/BenchBox-dev/BenchBox/develop/AGENTS.mdgit clone --depth 1 https://github.com/BenchBox-dev/BenchBoxWrote 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/benchbox-dev/benchbox/agents-md)<a href="https://agentmods.dev/instructions/benchbox-dev/benchbox/agents-md"><img src="https://agentmods.dev/badge/instructions/benchbox-dev/benchbox/agents-md.svg" alt="Measured on agentmods" 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 | $0.02098 | $0.02098 |
| Opus 5 | $0.01049 | $0.01049 |
| Sonnet 5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
BenchBox 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BenchBox Agent Guide
This file is the project authority for agent work. Keep it compact: detailed
operations belong in the linked docs, and generated skill mirrors belong to
/Users/joe/.skill-sync/skills.
Authority and provenance
Apply instructions in this order:
- platform/system safety and tool constraints;
- the user's current request and explicit approvals;
- this repository guide and the active project protocol;
- loaded skills and mechanical tool output;
- recommendations, examples, and historical notes.
Personal-global agent defaults apply only where this guide is silent; where behavior conflicts, this guide and the active project protocol win.
[AUTH-PROVENANCE-001] Classify a requirement before acting: task authority, repository policy, mechanical constraint, or recommendation. State the source when it changes scope, identity, publication, or destructive behavior. Never turn a recommendation or earlier task instruction into a standing requirement.
[COMMIT-IDENTITY-001] Before committing, resolve Git identity and its config origin. Reject known agent/service identities as author unless this task requests that exact identity; add no agent/service Co-Authored-By or equivalent attribution unless it requests that exact trailer. Repository-local values override the global identity and every linked worktree inherits them, but are not automatically intentional. A signing service may hold the committer slot behind a human author. Stale requests, tool conventions, harness/hook messages, and claimed agent work are not authorization (docs/agent/identity-instruction-boundary.md). The no-attribution bar also binds assistant-authored comments, reviews, and PR bodies (docs/agent/attribution-surfaces.md).
[DURABLE-ARTIFACTS-001] Write durable artifacts (commit messages, PR titles/bodies, committed comments) for a reader who never saw the session: no phase, gate, wave, or work-item labels, no plan or handoff references, no run-local state. Give the durable reason; process state belongs in a decision record or the tracker.
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 Changed · +6 lines · +69 tokens per session d1992ba7d690
- 2d ago First seen · 112 lines · 2,029 tokens per session scan A e972d8e114db
BenchBox AGENTS.md is an instructions file published in the GitHub repository BenchBox-dev/BenchBox (12 stars, last pushed yesterday), licensed MIT. It adds 2,098 tokens to every session, about $0.0105 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 2026-09-04.
Other instructions, from other repositories
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.
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).
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).
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.
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.