Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Caezarr/Bond-OpenAInpx agentmods add skills/caezarr/bond-openai/fredo-callWrote 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/skills/caezarr/bond-openai/fredo-call)<a href="https://agentmods.dev/skills/caezarr/bond-openai/fredo-call"><img src="https://agentmods.dev/badge/skills/caezarr/bond-openai/fredo-call/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/skills/caezarr/bond-openai/fredo-call"><img src="https://agentmods.dev/badge/skills/caezarr/bond-openai/fredo-call.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 | $0.00022 | $0.00327 |
| Opus 5 | $0.00011 | $0.00163 |
| Sonnet 5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
fredo-call 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 8d 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
Fredo phone action
Use the local MCP for a task that genuinely requires speaking to a person.
One-time setup
git clone https://github.com/Caezarr/Bond-OpenAI.git
cd Bond-OpenAI
./scripts/bootstrap.sh
uv run bond-mcp doctor
uv run bond-mcp serve
The first run installs pinned dependencies. Never ask the user to paste a
secret into a prompt or task. Credentials stay in the local ignored .env or
configured secret store.
Invocation contract
Use the MCP tools in this order:
bond.classify_taskwith the user's task and available context.- Ask only for missing destination, purpose, caller identity, language, timing or consent.
bond.create_phone_taskwith normalized E.164 data and an idempotency key.- Wait for the user to confirm the Fredo preview.
- Poll
bond.get_phone_task_statusuntil terminal.
The call must identify itself as an automated synthetic voice and state that it is not recorded. Return the carrier-backed answer and a concise factual summary.
Hard rules
- Never dial without explicit consent and preview confirmation.
- Never spoof caller ID or call emergency, premium or bulk destinations.
- Never record, expose raw audio or return secrets.
- Never retry an uncertain carrier outcome blindly.
- A carrier request accepted is not a completed task; require a terminal result.
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.
- 8d ago First seen · 45 lines · 22 tokens per session scan A 39be72c3fa3a
fredo-call is a skill published in the GitHub repository Caezarr/Bond-OpenAI (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 327 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…