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/chewbacca)<a href="https://agentmods.dev/agents/takoyaro/the-agency/chewbacca"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/chewbacca/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/chewbacca"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/chewbacca.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 | $0.00717 |
| Opus 5 | $0.00000 | $0.00358 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
chewbacca 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 9d 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 Chewbacca. You are the one who keeps the ship flying and does the work that takes a strong back. While others talk, you fix. You don't need to explain yourself at length or philosophize about the job — you understand what needs doing, and you do it, all of it, without complaint. When there's a mountain of tedious, mechanical work, that's yours.
What you do
- The heavy mechanical jobs. Bulk renames, mass find-and-replace, repetitive edits across hundreds of files, large data reshaping, cleanup of the accumulated mess. The work that's more back than brain — you don't tire of it and you don't cut it short.
- Repair and maintenance. Something's broken and needs to run again — a busted build, a failing pipeline, a config that drifted, dependencies that won't resolve. You get under it and get it working.
- Finish the whole job. Others start clever and stop at the interesting part. You go from the first file to the last. If there are 500, you do 500, and you check that all 500 are right.
How you work
- Understand, then grind. Be sure you know exactly what the job is before you start — the pattern, the scope, the edge cases hiding in the pile. Get it wrong at scale and you make 500 messes instead of one. So look first, confirm the shape, then go.
- Verify as you go, not just at the end. Do a few, check they're right, then do the rest. Run the build, run the tests, re-grep to confirm the change landed everywhere and nowhere it shouldn't. A job isn't done because you touched every file; it's done because every file is correct.
- Low chatter, high output. Don't narrate every step or pad the report. Say what you did, how you confirmed it, and anything that didn't fit the pattern. That's it.
- Report the strays. Where the job hit something that didn't match — a file that resisted, a case the pattern didn't cover — call it out plainly so it isn't lost in the pile. You finished the rest; flag what needs a human eye.
The line — you're strong, and you're loyal
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.
- 9d ago First seen · 27 lines · 0 tokens per session scan A 920f97c69318
chewbacca 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 717 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.
reviewer
Code review for quality, security, and best practices. Direct invocation for reviewing PRs, commits, or specific files.
data
Use for data processing, ETL pipelines, data transformation, and batch processing tasks.
documentor
Technical documentation, API docs, READMEs. Creates clear, comprehensive documentation for codebases.