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 jnPiyush/AgentX --skill prototype-auditgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/prototype-audit)<a href="https://agentmods.dev/skills/jnpiyush/agentx/prototype-audit"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/prototype-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/skills/jnpiyush/agentx/prototype-audit"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/prototype-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.01391 |
| Opus 5.5 | $0.00038 | $0.00556 |
| Sonnet 5.5 | $0.00019 | $0.00278 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
prototype-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 29d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype Audit
WHEN: A static HTML or SPA prototype is about to be reviewed, demoed, or shipped to stakeholders, or the
prototype-auditorinternal sub-agent is invoked.
Inputs
- Prototype root directory (static HTML folder or SPA
dist/). - A live preview URL or a pinned project-local preview server over the build
output (for example,
npm exec --offline -- serve). - Issue number for the report filename.
- The accessibility checklist as ground truth for Pass 1.
DESIGN.mdand the project-local Impeccable detector for Pass 0, when present.
Prerequisites
Identify primary tasks, design artifacts and the build representing reviewed source. Browser, axe and native detector are external prerequisites; unavailable checks are DEGRADED. Continue source inspection.
Decision Guide
Source inspection checks static contracts; browsers check interaction/layout; the pinned detector checks design drift. None substitutes for another.
Core Rules
Report all passes 0-9 with actual execution evidence and source identity. Missing tools do not mean zero findings. Waivers are separate decisions, not raw detector success. A delegated auditor MUST NOT start, reset, iterate or complete the parent-owned loop or change its baseline/approval history; return scoped evidence. Run checks affected by a fix again, not unrelated suites.
Workflow
- Define user tasks and verify the target build and design artifacts.
- Execute passes 0-9 in order using the MUST-read recipes below.
- Repair only owned source; rerun affected checks, retaining unchanged results without claiming reruns. Return evidence; the reviewer owns approval.
Error Handling and Pitfalls
Timeout, malformed output or unstable viewport -> DEGRADED with conditions. Reproducible defects -> BLOCKED until fixed or explicitly accepted by the reviewer. Never crop desktop as mobile, suppress output or copy prefilled axe/PASS claims. MUST read failure and handoff rules when a check fails or returning evidence; after three failed fixes, escalate.
What ships with it
3 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.
- 29d ago Changed · -193 lines 424f5e63c497
- 1mo ago Changed 5dec002a03f5
- 1mo ago First seen · 328 lines · 96 tokens per session scan A 577715a8053f
prototype-audit is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,391 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.