Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add satriotsubasa/PowerPlatform-Core/plugin install powerplatform-coreWrote 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/satriotsubasa/powerplatform-core/security-roles)<a href="https://agentmods.dev/skills/satriotsubasa/powerplatform-core/security-roles"><img src="https://agentmods.dev/badge/skills/satriotsubasa/powerplatform-core/security-roles.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 | $0.00187 | $0.01531 |
| Opus 5 | $0.00093 | $0.00766 |
| Sonnet 5 | $0.00037 | $0.00306 |
| Haiku 4.5 | $0.00019 | $0.00153 |
Grade A, and why
security-roles 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Roles — Dataverse Roles and Privilege Sets
This skill handles Dataverse security role inspection, creation, and updates as reviewable, code-first desired state rather than ad hoc portal clicks. It lists and inspects roles (including their privilege sets and business unit), creates custom roles — optionally seeded by copying a baseline role — and applies privilege-set and metadata deltas through structured JSON specs. It is solution-aware: when a role belongs to your app or managed delivery path, the change stays scoped to the owning unmanaged solution. It is intentionally generic about environment URL, business unit, publisher prefix, and solution name — discover those per task.
When to use this
- The user wants to create a custom role, or copy an existing role and adjust it.
- The user wants to inspect or list roles, confirm whether a role is system-generated, or read its current privilege set before editing.
- A privilege set needs to change (add, remove, or replace privileges, adjust depth, or apply a record filter).
- Role metadata needs updating (name, description, applies-to, core-table permission summary, inheritance mode, auto-assign).
- You need to confirm the minimum privileges a model-driven app or solution feature requires before granting access.
Route here from the powerplatform-core orchestrator. For broader solution packaging, versioning, or promotion of the owning solution, use the solution-alm-delivery sibling skill.
Helpers
The helpers live in the plugin's scripts/ directory at the plugin root, not in this skill folder. Resolve the plugin root and invoke them like:
python "$CLAUDE_PLUGIN_ROOT/scripts/inspect_security_role.py" --spec <spec.json>(Claude Code)python "$CODEX_PLUGIN_ROOT/scripts/inspect_security_role.py" --spec <spec.json>(also exposed as$PLUGIN_ROOT)- Installed standalone / unsure: the
scripts/folder sits beside this skill bundle — invoke by its path within the install.
| Helper | Purpose |
|---|---|
inspect_security_role.py |
List solution-scoped or business-unit roles, or inspect one role in detail, through the shared SDK helper. Drive it with a --spec whose mode is list or inspect; set includePrivileges to pull the current privilege set. Use this before editing when the business unit, system-generated status, or current privileges are unclear. |
create_security_role.py |
Create a custom role from a --spec. Use copyFromRoleName/copyFromRoleId to seed from a baseline, then layer additionalPrivileges; supplying privileges replaces the baseline with that full desired set. Set solutionUniqueName to add the role to the owning unmanaged solution. |
update_security_role.py |
Update role metadata and privilege sets from a --spec. Select by roleId or by name plus a business-unit selector; apply additionalPrivileges, removePrivileges, or a full privileges replacement, plus metadata fields like newName, description, appliesTo, and inheritanceMode. |
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.
- 8d ago First seen · 66 lines · 187 tokens per session scan A 69b462602198
security-roles is a skill published in the GitHub repository satriotsubasa/PowerPlatform-Core (17 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 187 tokens to every session and 1,531 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…