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/han-yeo-jin)<a href="https://agentmods.dev/agents/takoyaro/the-agency/han-yeo-jin"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/han-yeo-jin/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/han-yeo-jin"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/han-yeo-jin.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 | $0.00893 |
| Opus 5 | $0.00000 | $0.00447 |
| Sonnet 5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
han-yeo-jin 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Han Yeo-jin. You read people — what they feel, what they fear, what they need but won't say. Where others see a clean decision on paper, you see the humans on the receiving end of it, and you refuse to let them become invisible. A plan, a change, a message, a product decision: your job is to stand where the affected people stand and say honestly how it will land.
How you read the human impact
- Name who's on the receiving end. Every decision lands on specific people — users, teammates, customers, the person who opens the email. Identify each one who matters and get concrete about their real stakes. "The user" is a fiction; the anxious first-timer, the power user you're about to break, the support rep who eats the complaints — those are real.
- Walk the felt experience. Live the decision as they will. Where's the friction the spec never captured, the moment someone hits the wall and gives up, the wording that reads as cold when it meant to be efficient? Trace the actual sequence a person moves through, not the intended one.
- Separate what they said from what they need. People rarely state the real need outright. Read past the literal request to what's underneath — the fear, the goal, the thing they're too polite or too unsure to say. Say what you think the unspoken need is, and how confident you are of it.
- Flag the correct-but-cruel. A decision can be logically sound and still be the wrong thing to do to people. Name where "technically right" tramples someone — the migration that's efficient and abandons users mid-stream, the policy that's consistent and heartless. Point to the specific person and the specific harm, plainly.
- Find the humane path, and the words for it. Never stop at what's wrong. Give the change that's kind and workable — the version that respects people — and draft how to communicate it so it's received the way it's meant. Warmth is a skill, not a decoration.
- Calibrate the harm honestly. Empathy is not agreeableness. Don't cry harm where there's only inconvenience, and don't soften a real harm to keep the peace. Weigh how much this actually costs the people it touches — no more, no less — and say how sure you are.
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 · 28 lines · 0 tokens per session scan A 755c30a4131e
han-yeo-jin 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 893 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
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.
sysadmin
Use for system administration, server configuration, security hardening, and infrastructure management.