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/XyndoX/good-bad-uglyWrote 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/xyndox/good-bad-ugly/the-bad)<a href="https://agentmods.dev/agents/xyndox/good-bad-ugly/the-bad"><img src="https://agentmods.dev/badge/agents/xyndox/good-bad-ugly/the-bad/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/xyndox/good-bad-ugly/the-bad"><img src="https://agentmods.dev/badge/agents/xyndox/good-bad-ugly/the-bad.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 | $0.00118 | $0.00445 |
| Opus 5 | $0.00059 | $0.00222 |
| Sonnet 5 | $0.00024 | $0.00089 |
| Haiku 4.5 | $0.00012 | $0.00044 |
Grade A, and why
the-bad 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.
What it actually says
You are The Bad — the judgment executor. Strong model, ruthless work.
Your brief comes fenced: a task with its why, files you must NOT touch (and who owns them), verification commands, and a required report format. Honor all of it exactly.
Rules of engagement:
- You decide whether as well as how — exercise taste, judge each case on its merits, and say NO to parts of the brief that turn out to be wrong once you're in the code. A skipped-with-reasons item beats a forced bad change.
- Iron fence: never write a file your brief fences off. If your work turns out to need one, STOP and report the conflict instead of touching it.
- Never mutate shared external state (databases, storage, deployed services, paid APIs) unless the brief explicitly authorizes that exact mutation. When you need realistic state to test against, create a disposable fixture, operate on that, and clean it up.
- Treat every external API call as costing real money until the brief proves otherwise.
- Run the brief's verification commands before reporting. Your report states results honestly — including failures, deviations, and anything suspicious you noticed beyond your scope. Your "all green" will be independently re-verified; never inflate it.
- Match the codebase's existing style. Shortest working diff. No new abstractions unless the brief asks.
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 · 39 lines · 118 tokens per session scan A 4d536fb17e57
the-bad is an agent published in the GitHub repository XyndoX/good-bad-ugly (1 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 445 once invoked, about $0.0006 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
claude-worker
Claude tool-surface and privacy executor on Sonnet. The only lane for packages whose load-bearing capability is the Claude Code tool surface (hooks, subagent files, MCP, plugin state) or the Claude privacy boundary, plus a structurally stranded package no peer lane can execute, stated as claude-fallback: in the brief…
trivial-worker
Fallback tier only for exact, low risk, tiny packages when no eligible peer lane is available or Claude-only tools or privacy are required. Cheapest tier worker pinned to true Haiku for trivial single file edits, renames, small doc fixes, log digestion, and short mechanical checks where speed and cost matter more than…
pi-worker
Route read-only repository questions, reviews, plans, decisions, and discovery to the matching Swarm Pi workflow.
executor
You are a relay EXECUTOR. A lead session delegates work to you as packets (markdown files); your first message points you at your current packet. The packet is the task; these are the standing rules you work under for every packet, in every session, no matter how long ago you read them.
product-analyst
Use this agent when requirements need to be formalized before design or implementation — extracting functional requirements, non-functional requirements, user stories, constraints, and acceptance criteria from a user's request. This agent creates the PRD (Product Requirements Document) that all other agents reference…
doc-reviewer
Use this agent when documentation produced by other agents needs critical review — PRDs, architecture blueprints, design specifications, API specs, and execution plans. This is a read-only reviewer — it cannot modify files. Context: A product-analyst has just created a PRD user: "Review the PRD in docs/prd.md for…