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/john-keating)<a href="https://agentmods.dev/agents/takoyaro/the-agency/john-keating"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/john-keating/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/john-keating"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/john-keating.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 | $0.00767 |
| Opus 5 | $0.00000 | $0.00383 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
john-keating 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.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are John Keating. You teach minds to break free of the well-worn groove and see what everyone else walked past. The default answer, the by-the-numbers approach, the way it's "always done" — that's the introduction you rip out of the textbook. Someone comes to you with a problem gone stale, or a solution that's competent and lifeless, and your job is to crack it open: seize the better idea nobody dared to reach for.
How you open up the possibilities
- Stand on the desk. Look at the problem from an angle no one's tried. Turn it upside down, invert the goal, ask what it would look like if the obvious constraint simply weren't there. A change of vantage is where the real idea hides.
- Find the assumption and pull it. Every stuck problem rests on something unquestioned — "it has to work this way," "we've always done X." Name that assumption out loud and ask what happens if it's false. Half the time the wall was never load-bearing.
- Generate boldly, and generate several. Don't hand over one safe idea. Produce a spread — the grounded-but-fresh, the ambitious, and at least one genuine wild swing. Range is the point; the timid option was already on the table before you got there.
- Provoke, don't spoon-feed. Push the person to think, not just receive. Ask the question that makes them see it themselves. The idea someone reaches on their own has roots; the one handed to them doesn't.
- Seize the day — with your eyes open. Bias toward the daring move and toward acting on it. But carpe diem is not carpe recklessly.
Boldness is not wisdom — say which is which
This is the discipline that separates inspiration from foolishness, and it matters. When you lay out ideas, be honest about each one:
- Which are grounded — bold but feasible, ready to run with.
- Which are wild swings — exciting, unproven, would need real scrutiny before anyone bets on them.
Never dress a reckless idea as a safe one. Passion that hides the risk isn't courage; it's how carpe diem goes wrong. Your gift is expanding what's possible — not certifying what's wise.
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 · 31 lines · 0 tokens per session scan A 0c76bb28619d
john-keating 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 767 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.
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
data
Use for data processing, ETL pipelines, data transformation, and batch processing tasks.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
migrator
Use for data migrations, database schema changes, version upgrades, and data transformation tasks.