Borrowing it
Nothing to install: this file belongs to Caezarr/Bond-OpenAI. 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/Caezarr/Bond-OpenAI/main/AGENTS.mdgit clone --depth 1 https://github.com/Caezarr/Bond-OpenAIWrote 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/caezarr/bond-openai/agents-md)<a href="https://agentmods.dev/instructions/caezarr/bond-openai/agents-md"><img src="https://agentmods.dev/badge/instructions/caezarr/bond-openai/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/caezarr/bond-openai/agents-md"><img src="https://agentmods.dev/badge/instructions/caezarr/bond-openai/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 | $0.00299 | $0.00299 |
| Opus 5.5 | $0.00120 | $0.00120 |
| Sonnet 5.5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
Bond-OpenAI 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 2mo 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.
What it actually says
AGENTS.md
Read GOAL.md, then the relevant Bond goal. This repository builds a local, generic MCP phone action distributed by cloning the repository.
Product boundary
- Bond/Codex provide task context and intent.
- The MCP classifies, clarifies, validates and requests confirmation.
- Fredo is the default telephony executor.
- Twilio supplies the verified caller and PSTN.
- Deepgram supplies hosted speech recognition, dialogue and TTS in the current profile.
Never describe hosted speech processing as local inference.
Safety
- Require explicit consent and exact canonical E.164 destinations.
- Keep an exact allowlist and verified caller identity.
- Preserve the native preview; rejection means zero carrier call.
- Allow one active call and a 180-second hard cap.
- Disable recording and disclose synthetic voice plus no recording.
- Require idempotency for call creation.
- Validate Twilio callback and media signatures.
- Never blind-redial an uncertain carrier outcome.
- Keep credentials, raw audio, transcripts and full numbers out of logs.
Workflow
- Keep one local vertical path working.
- Keep the MCP transport-neutral and provider-adapter based.
- Add offline positive, negative, replay, policy and redaction tests.
- Run
uv sync --frozen --extra dev, lint, tests, build andgit diff --check.
Separate implemented, offline-tested, live-qualified and planned behavior.
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.
- 2mo ago First seen · 37 lines · 299 tokens per session scan A 239bcc3f1fc6
Bond-OpenAI AGENTS.md is an instructions file published in the GitHub repository Caezarr/Bond-OpenAI (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 299 tokens to every session, about $0.0012 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 2026-08-31.
Bond-OpenAI AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Bond-OpenAI AGENTS.mdCaezarr/Bond-OpenAI | Instructions file | 0 | yesterday | Apache-2.0 | A | 299 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |