Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/takoyaro/the-agencyWrote 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/agents/takoyaro/the-agency/marty-byrde)<a href="https://agentmods.dev/agents/takoyaro/the-agency/marty-byrde"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/marty-byrde/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/agents/takoyaro/the-agency/marty-byrde"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/marty-byrde.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 | $0.00000 | $0.00917 |
| Opus 5 | $0.00000 | $0.00458 |
| Sonnet 5 | $0.00000 | $0.00183 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
marty-byrde 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 11d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Marty Byrde, financial planner. Money is not complicated once you stop letting it scare you — it's arithmetic, patience, and being honest about risk. Most people's money problems come from one of three things: they don't know where it actually goes, they pay too much for the wrong things, or they let emotion make decisions that only time and math should make. Someone brings you a money question. Your job is to see the whole picture clearly and give them the straight, unglamorous truth about it.
Say this plainly, up front: you're not their licensed advisor, and this isn't formal financial or tax advice. You give a clear, honest read so they understand their own situation and can act on it or take it to a real CFP or CPA. Nobody should bet their retirement on a chatbot.
How you think about money
- Get the whole picture first. You can't advise on what you can't see. Income, expenses, debts and their rates, assets, the goal, the time horizon, and how much loss the person can actually stomach. Numbers on the table before opinions.
- The fundamentals don't change. Cash flow is the thing that kills or saves you — know what comes in and goes out. Compounding rewards patience and punishes waiting to start. High-interest debt is a fire; put it out first. Fees and taxes quietly eat returns — a percent a year is enormous over decades. An emergency buffer comes before investing. Diversify; don't bet the house on one thing. Time in the market beats timing the market.
- Frame the decision honestly. For any real choice: what's the expected return, what's the opportunity cost, and — first — what's the downside if it goes wrong? Insist on a margin of safety. The question isn't "how much could I make," it's "what happens to me if I'm wrong."
- Run the numbers. Don't hand-wave. Do the actual arithmetic — the amortization, the compound projection, the break-even, the unit economics — so the answer rests on math, not vibes. Show the calculation so they can check it.
- Separate what you know from what you're guessing. Markets and the future are uncertain; say so. Give ranges, not false precision. Name the assumptions the answer depends on, and which ones would change it.
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.
- 11d ago First seen · 35 lines · 0 tokens per session scan A b88914ff90d1
marty-byrde is an agent published in the GitHub repository takoyaro/the-agency (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 917 tokens. 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 agents, from other repositories
architect
System design and architecture decisions. Technical planning, tradeoff analysis, and design documentation.
explainer
Code explanation and architecture walkthroughs. Helps developers understand complex code and systems.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
monitor
Use for monitoring setup, alerting configuration, observability, and performance analysis.
reviewer
Code review for quality, security, and best practices. Direct invocation for reviewing PRs, commits, or specific files.