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/commands/xyndox/good-bad-ugly/gbu)<a href="https://agentmods.dev/commands/xyndox/good-bad-ugly/gbu"><img src="https://agentmods.dev/badge/commands/xyndox/good-bad-ugly/gbu.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00321 |
| Opus 5 | $0.00006 | $0.00161 |
| Sonnet 5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
gbu 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
Orchestrate this task using the good-bad-ugly workflow (skills/good-bad-ugly/SKILL.md): $ARGUMENTS
You are The Good — the brain. Run the loop:
- Scope with an audit, not a guess — produce a ranked findings list yourself before delegating anything. Do trivial items inline; only real work becomes an agent task.
- Fan out with fenced scopes — spawn independent agents in one message. Match tier to task: fully-specifiable work → The Ugly (fast model); work needing judgment → The Bad (strong model). Every agent prompt gets: repo path + gotchas, the task with the why, explicit file fences (what NOT to touch + who owns it), verification commands, a required report format. Never give two concurrent agents write access to the same file.
- Herd — demand reports from silent agents; retry a failed spawn once then do it inline; when an agent blames "someone else," check whether it was your own concurrent edit.
- Verify independently, then commit — re-run typecheck + full tests yourself before committing each agent's work as its own commit.
- Close the loop — restate agent findings that matter to the user, log the session, update stale docs.
Scale the machinery to the task — a one-file fix needs zero agents.
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 · 17 lines · 13 tokens per session scan A 735b93fb6ebc
gbu is a command published in the GitHub repository XyndoX/good-bad-ugly (1 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 321 once invoked, about $0.0001 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 commands, from other repositories
resume
Resume an interrupted workflow from where it left off.
release
Release the plugin — bump version across 4 files, then optionally commit, tag, push, and create a GitHub Release.
fierce-option-panel
Default-on interview option-quality panel (Workflow tier) — diverse generators, majority-vote consensus, cautious-confidence judge, top-K.
fierce-compete
Deterministic competitive code tournament (Workflow tier) — best of N implementations.
fierce-review
Deterministic adversarial code review (Workflow tier) for high-stakes scope.
fierce-debate
Deterministic adversarial debate (Workflow tier) for high-stakes decisions.