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 skills add Destynova2/cli-code-skills --skill cli-audit-wizardgit clone --depth 1 https://github.com/Destynova2/cli-code-skillsWrote 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/skills/destynova2/cli-code-skills/cli-audit-wizard)<a href="https://agentmods.dev/skills/destynova2/cli-code-skills/cli-audit-wizard"><img src="https://agentmods.dev/badge/skills/destynova2/cli-code-skills/cli-audit-wizard/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/skills/destynova2/cli-code-skills/cli-audit-wizard"><img src="https://agentmods.dev/badge/skills/destynova2/cli-code-skills/cli-audit-wizard.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 | $0.00119 | $0.06554 |
| Opus 5.5 | $0.00048 | $0.02622 |
| Sonnet 5.5 | $0.00024 | $0.01311 |
| Haiku 4.5 | $0.00012 | $0.00655 |
Grade B, and why
cli-audit-wizard scanned grade B with 2 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
| +-- ~/.netrc (legacy but common) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- CLI wraps API: `tool reload` is sugar over `curl -X POST /load` How it starts
The opening of the file, as written. The whole thing — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimization: This skill uses on-demand loading. Heavy content lives in
references/and is loaded only when needed.
Language rule: Skill instructions are written in English. When generating user-facing output, detect the project's primary language (from README, comments, docs, commit messages) and produce the report in that language. If the project is bilingual, ask the user which language to use before proceeding.
Audit Wizard -- Wizard Quality Index (WQI)
Audit configuration wizards for UX quality, lifecycle completeness, and multi-surface exposure (CLI, MCP, web).
"The worst time for users to make choices is before they've started using the system." -- OpenBSD design philosophy
Natural laws mapped to wizard rules
Each analogy maps to a concrete, testable audit check. Only actionable rules are listed here.
| Source | Wizard rule (testable) |
|---|---|
| Seed germination | Ask 3-5 seed values max. If more, you're encoding the tree in the seed |
| Axolotl (facultative metamorphosis) | Never show advanced options by default. --advanced is opt-in |
| Immune system | Doctor checks are pattern-based (schema, connectivity), not intent-based |
| Homeostatic set point | wizard apply is idempotent: run 1x or 100x, same result (the idempotence/determinism toolkit is shared in ../shared/determinism.md) |
| Tardigrade (cryptobiosis) | Every config section has a safe degraded state when dependencies are down |
| Principle of least action | Every question must reduce configuration entropy. Derivable = don't ask |
| 2nd law of thermodynamics | Config drifts without doctor. Doctor is the energy that fights entropy |
| Hick's Law | Max 5 options per prompt. More? Filter or nest |
| Miller's Law | Max 7 fields per wizard screen. Group into chunks |
| Recognition > recall | Pre-fill values on re-run. Enter-through should produce working config |
| Portal's 4-step | Each wizard step teaches one concept. Never combine two new things |
| Save/checkpoint | Auto-backup config before every destructive apply |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 545 lines · 119 tokens per session scan B 3fc107c29e34
cli-audit-wizard is a skill published in the GitHub repository Destynova2/cli-code-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 6,554 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
excalidraw-cli
Create editable Excalidraw flowcharts and diagrams, or export .excalidraw files to PNG or SVG.
feat
Skill "feat" from UfoMiao/zcf, covering core workflow, 1. input analysis and type determination, 2. classification processing mechanism, 3. key execution principles and quality assurance points.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…