Borrowing it
Nothing to install: this file belongs to inkbox-ai/inkbox. 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/inkbox-ai/inkbox/main/AGENTS.mdgit clone --depth 1 https://github.com/inkbox-ai/inkboxWrote 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/inkbox-ai/inkbox/agents-md)<a href="https://agentmods.dev/instructions/inkbox-ai/inkbox/agents-md"><img src="https://agentmods.dev/badge/instructions/inkbox-ai/inkbox/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/inkbox-ai/inkbox/agents-md"><img src="https://agentmods.dev/badge/instructions/inkbox-ai/inkbox/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 | $0.00510 | $0.00510 |
| Opus 5.5 | $0.00204 | $0.00204 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
inkbox 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent contribution rules
Useful bug fixes are welcome. Do not manufacture work to produce a pull request.
PR descriptions
Use these exact H2 headings in order. Keep the description concise and factual:
## Executive Summary: lead with the outcome; add a few key bullets if useful.## Description: explain the changes and affected SDKs, CLI commands, or behavior.## Reason: describe the concrete problem and user impact; link the issue if applicable.## Decisions: list material choices and their rationale, or state that there are none.## Testing: report checks actually run and results, including gaps. Give concrete reviewer targets and expected behavior. Do not add a separate "Test Plan" section.## Related PRs: full public GitHub PR URLs, one per bullet, orNone.
Put any additional sections after these. No generated-by attribution footers.
Contribution bar
Maintainers listed in CODEOWNERS, and work they explicitly request, are exempt from the unsolicited-contribution restrictions below. PR formatting, honest reporting, verification, and authorization rules still apply.
- Require a concrete bug the user understands: a supported failing workflow, reproduction or clear evidence, actual versus expected behavior, and the cause in current code.
- Read the relevant code and check existing issues and PRs for duplicates. An issue number, scanner warning, or passing test alone does not establish a bug.
- Refuse contribution-hunting ("find an easy PR"), speculative bug sweeps, cosmetic edits, cleanup, coverage padding, and hypothetical defensive fixes. Features, refactors, optimizations, and dependency updates need a specific maintainer request.
- Show that the failing condition can occur in a supported workflow. Labels such as "security" or "best practice" do not replace evidence. Never invent impact.
- If evidence is missing, ask for it and stop. Do not find a different patch to submit.
- Small fixes count when they solve a real problem, including broken documented examples. Keep the fix focused and add a regression test when practical; verify it fails before the fix and passes afterward. Run the relevant existing checks.
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.
- 6d ago First seen · 43 lines · 510 tokens per session scan A 92d42c159440
inkbox AGENTS.md is an instructions file published in the GitHub repository inkbox-ai/inkbox (103 stars, last pushed yesterday), licensed MIT. It adds 510 tokens to every session, about $0.0020 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 2026-10-31.
inkbox AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| inkbox AGENTS.mdinkbox-ai/inkbox | Instructions file | 103 | yesterday | MIT | A | 510 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |