power-platform-developer-suite: Skill for Claude Code

.claude/skills/audit-capture/SKILL.md

audit-capture is a skill for Claude Code from joshsmithxrm/power-platform-developer-suite. It costs 37 tokens per session (1,585 once invoked), scanned A, original, MIT.

A command-line capture tool that records terminal interfaces and extension screens as PNG files, with metadata describing what was captured. It follows a manifest, which is a list of required screens and capture settings.

In plain words
What is it for?
Use it to capture all or selected TUI screens and extension panels, check manifest entries, and produce files for a designer or Claude audit session.
Why use it?
It creates consistent input for a design review without requiring someone to capture every screen by hand. It is for design audits, not for comparing changes over time.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is joshsmithxrm/power-platform-developer-suite's own configuration. It tells Claude Code how to work on power-platform-developer-suite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything power-platform-developer-suite configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash(node tools/audit-capture*), Bash(node tools/audit-capture.mjs *), Bash(npm run audit*).

Reuse

Borrowing it

Nothing to install: this file belongs to joshsmithxrm/power-platform-developer-suite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joshsmithxrm/power-platform-developer-suite/main/.claude/skills/audit-capture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suite

Made for: Claude Code.

Wrote 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.

agentmods badge for audit-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/audit-capture.svg)](https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/audit-capture)
Your own site
<a href="https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/audit-capture"><img src="https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/audit-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01585
Opus 5 $0.00018 $0.00792
Sonnet 5 $0.00007 $0.00317
Haiku 4.5 $0.00004 $0.00159

Measured 6d ago against content hash 295fbd49c067, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-capture 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 6d 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.

.claude/skills/audit-capture/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Capture

Manifest-driven capture of every user-facing PPDS surface. Produces PNGs + meta.json + root manifest.json under $AUDIT_OUT/ per ppds-design-system/AUDIT-SCHEMA.md. Output is consumed by a Claude audit session (or human designer) against our design system.

When to Use

  • Before a design-audit round — capture a clean baseline of every surface
  • After UI shakedown / visual fixes land, to refresh the baseline
  • When adding a new TUI screen or extension panel, to verify the manifest entry reaches it
  • NOT for regression testing — this is audit input, not a diff tool

Quick start

# One capture run, all surfaces, local output
export AUDIT_OUT="$TEMP/ppds-audit-$(date +%s)"
export PPDS_PROFILE=dev                 # optional — unlocks connected captures
export PPDS_ENV=test-env                 # optional — unlocks connected captures
node tools/audit-capture.mjs run all

# Single surface
node tools/audit-capture.mjs run tui
node tools/audit-capture.mjs run extension

# Dry-run a manifest without capturing
node tools/audit-capture.mjs validate tui

# List manifest entries
node tools/audit-capture.mjs list extension

Exit codes: 0 = everything ok or skipped, 1 = at least one entry errored.

Required environment

Var Required Purpose
AUDIT_OUT yes Absolute path, outside the repo working tree. Runner refuses relative or in-repo paths.
PPDS_PROFILE no Profile name. Entries with requires: connected are skipped without it.
PPDS_ENV no Environment name. Skipped same as above.
AUDIT_REDACT no true (default) masks identifying values in status bars. Set false for raw.
AUDIT_SOURCE_REPO / _REF / _COMMIT no Overrides the git metadata recorded in manifest.json. CI uses these.

Output layout

Per AUDIT-SCHEMA.md:

Read the full file on GitHub · 131 lines

Changes

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.

  1. 6d ago First seen · 131 lines · 37 tokens per session scan A 295fbd49c067

Subscribe to this mod's changes

audit-capture is a skill published in the GitHub repository joshsmithxrm/power-platform-developer-suite (7 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 1,585 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

dynamics365-expert

Expert in Dynamics 365 platform, model-driven apps, canvas apps, Power Automate flows, Dataverse, plugins, and custom workflows. Use when the user mentions Microsoft platforms, ERP, CRM, business apps, the Power Platform, or Dataverse, or when the task involves Dynamics 365 Applications, Dataverse Platform…

personamanagmentlayer/pcl · 80 tokens

get-context

Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.

XiaomiMiMo/MiMo-Code · 46 tokens

frontend

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines…

code-yeongyu/lazycodex · 183 tokens

deck-graphify-dark

深夜渐变 + 漂浮 orbs + SVG 力导向图谱 + JetBrains Mono.

nexu-io/html-anything · 28 tokens

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens

antv-x6-editor

Use this skill whenever the user wants to create, customize, or troubleshoot X6 v3 graph editor diagrams. Triggers include: any mention of 'X6', 'antv x6', '@antv/x6', 'X6 editor', 'X6 图编辑', '流程图', 'DAG', 'ER图', '实体关系图', '血缘图', '组织架构图', 'UML类图', 'flowchart', 'DAG diagram', 'ER diagram', 'lineage graph', 'org chart'…

antvis/chart-visualization-skills · 253 tokens