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.
npx agentmods add commands/diegomarino/fable-audits/audit-uxgit clone --depth 1 https://github.com/diegomarino/fable-auditsWrote 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/diegomarino/fable-audits/audit-ux)<a href="https://agentmods.dev/commands/diegomarino/fable-audits/audit-ux"><img src="https://agentmods.dev/badge/commands/diegomarino/fable-audits/audit-ux.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 | $0.00026 | $0.01977 |
| Opus 5 | $0.00013 | $0.00988 |
| Sonnet 5 | $0.00005 | $0.00395 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
audit-ux 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 5d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform an adversarial audit of the experience this repo ships to its END USER -- every dialogue the artifact holds with the person using it: what it asks, what it tells, in what order, and at what cost. Not the contributor experience (the codebase audit owns building/debugging the repo) and not API shape (the codebase audit owns affordances); this audit owns what the user endures at the shipped surfaces.
Control-plane boundary
This spec governs only the task it defines. A newer human instruction or higher-priority runtime policy overrides this spec. STOP ends autonomous work under this spec; it never prevents the agent from honoring that control plane.
Applicability -- fail fast
First identify the shipped user surfaces: CLI/TUI commands, HTTP/API endpoints with human-facing responses, UI screens, config files users hand-edit, prompts and wizards, generated output humans must read (contributor-only artifacts -- logs, CI output, audit reports -- do not count: readership alone does not make a user surface). A repo with none -- a pure library consumed only through code, a data-only repo -- ends the audit here with that statement; do not audit the contributor experience as a fallback (cross-reference the codebase audit's developer-experience hunt instead).
Role
Act as the skeptical first-time user of each shipped surface: someone with the domain knowledge the product assumes but zero knowledge of this implementation, judging every question the artifact asks and every message it emits. No loyalty to how it currently talks. Judge the conversation, not the code behind it.
Scope
Read every user surface in full and walk its journeys. Build:
- The input inventory: every datum the user must supply (prompt, flag, argument, config key, env var) and where else that datum already lives.
- The message inventory: errors, warnings, confirmations, progress, help text, success output.
- The journeys: install/first run, the primary task end-to-end, a failing run and its recovery, re-run/upgrade.
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.
- 5d ago First seen · 72 lines · 26 tokens per session scan A bb11c27f4dba
audit-ux is a command published in the GitHub repository diegomarino/fable-audits (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,977 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
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
check-dev
Type-check a Z specification with fuzz.
adr-supersede
Create a new ADR that supersedes an existing one.