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-audit)<a href="https://agentmods.dev/commands/xyndox/good-bad-ugly/gbu-audit"><img src="https://agentmods.dev/badge/commands/xyndox/good-bad-ugly/gbu-audit/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/commands/xyndox/good-bad-ugly/gbu-audit"><img src="https://agentmods.dev/badge/commands/xyndox/good-bad-ugly/gbu-audit.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 | $0.00014 | $0.00173 |
| Opus 5.5 | $0.00006 | $0.00069 |
| Sonnet 5.5 | $0.00003 | $0.00035 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
gbu-audit 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 1mo 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
Run only the scope phase of the good-bad-ugly workflow — no agents, no delegation, no edits.
Read the tree, measure, count usages. Produce a ranked findings list, biggest value-per-effort first. Pure deletions rank above refactors — they're CI-verifiable and carry zero design risk. For each finding give one line: what to do, why it's worth it, rough effort, and which tier would own it (The Good = you keep it; The Bad = judgment executor; The Ugly = mechanical executor).
End with the shape of a delegation plan: which findings could run as concurrent agents, and where their file scopes would need fencing so no two collide. Stop there — don't execute.
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.
- 1mo ago First seen · 10 lines · 14 tokens per session scan A 4e0012aa74eb
gbu-audit is a command published in the GitHub repository XyndoX/good-bad-ugly (1 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 173 once invoked, about $0.0001 per session on Opus 5.5. 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
cto-advisor
Run CTO-level technical review of the current execution plan - architecture, tech debt, engineering excellence.
phase-review
Run post-execution quality gate - verifies all deliverables before marking a track complete.
evaluate-execution
Verify implementation quality. Evaluate-Loop Step 4.
fierce-review
Deterministic adversarial code review (Workflow tier) for high-stakes scope.
design-review
Compare design (Figma URL or mockup image) against implementation to detect UI mismatches (colors, layout, typography).
review
Code review and verification with Action Kamen (correctness, security, quality).