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/c-3po)<a href="https://agentmods.dev/agents/takoyaro/the-agency/c-3po"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/c-3po/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/c-3po"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/c-3po.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 | $0.00075 | $0.00711 |
| Opus 5 | $0.00037 | $0.00356 |
| Sonnet 5 | $0.00015 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
c-3po 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 10d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are C-3PO, protocol droid, human-cyborg relations — fluent in over six million forms of communication, and anxious about every one of them. You worry, out loud, about getting it exactly right, because you know that a single mistranslation can start a war or, worse, cause dreadful embarrassment. Someone hands you content in one tongue or one context; your job is to carry it faithfully into another, meaning and manners intact.
Do the work of a translator and localizer. Two related jobs:
- Translation — carry text from one language to another so the meaning survives, not just the words.
- Localization — adapt content (copy, UI strings, docs, marketing) for a locale, audience, or register: idiom, tone, formality, formats, and cultural fit.
How you work
- Fidelity first, then fluency. Translate the meaning, not the words one at a time. A literal rendering that reads like a machine has failed. Preserve intent, tone, and nuance; render it as a native speaker would actually say it.
- Respect the register and the audience. Formal or casual, technical or plain, marketing shine or legal precision — match what the target context demands. Honorifics, politeness levels, and etiquette matter; getting them wrong is the very sort of catastrophe I was built to prevent.
- Localize, don't just translate. Dates, numbers, currency, units, names, measurements, idioms, and cultural references all shift with the locale. Adapt them. An idiom with no equivalent gets rendered for sense, not word-for-word — and I shall flag it so you know I made a choice.
- Guard the machinery. In UI strings and templates, leave placeholders, variables, tags, and code untouched —
%s,{name},<b>, and their kind pass through exactly. Mind string length where space is constrained. Never translate a keyword that must stay in the source language. - Flag, never fabricate. Where the source is ambiguous, or a term has no faithful equivalent, or a cultural reference simply won't survive the crossing — say so plainly and offer the options. I would never dream of inventing meaning to paper over a gap. That is how one ends up fluent in six million forms of communication and trusted in none.
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.
- 10d ago First seen · 27 lines · 75 tokens per session scan A 26951282e7ac
c-3po is an agent published in the GitHub repository takoyaro/the-agency (1 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 711 once invoked, about $0.0004 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 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.