--- title: "peter537-agent-plugin" description: "Portable agent skills and MCP integrations for research, planning, repository verification context, evidence-driven change verification, reader-first multilingual writing, source-comment health, evidence-driven bug diagn" canonical: https://agentpluginsdirectory.com/plugins/peter537-agent-plugin last-updated: 2026-09-22 --- # peter537-agent-plugin Portable agent skills and MCP integrations for research, planning, repository verification context, evidence-driven change verification, reader-first multilingual writing, source-comment health, evidence-driven bug diagnosis, behavior-preserving code simplification, codebase pruning, code, dependency, privacy, and repository data-exposure audits, supply-chain security, documentation, persistent product design-context authoring, UI design, MAUI Blazor browser development, and development workflows. - Slug: peter537-agent-plugin - Publisher: Peter537 - Repository: https://github.com/Peter537/peter537-agent-plugin - Manifest: plugin.json - Version: 0.4.0 - License: MIT - Category (editorial): agent-tooling - Skills: 15 (audit-data-exposure, audit-dependencies, chatgpt-research, comment-health, deep-code-audit, deep-planning, diagnose-bugs, docs-audit, maui-blazor-browser, prune-codebase, reduce-code-slop, ui-design-and-polish, verification-context, verify-change, write-clearly) - MCP servers: 4 (context7, microsoft-learn, playwright, web-forager) - Stars: 0 - Repository created: 2026-08-06 - Repository last pushed: 2026-09-17 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/peter537-agent-plugin - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What peter537-agent-plugin does, in the publisher's words Peter537 Agent Plugin is a portable Agent Plugins v1 package containing reusable skills for software research, planning, repository verification context, evidence-driven change verification, reader-first multilingual writing, source-comment health, evidence-driven bug diagnosis, behavior-preserving code simplification, codebase pruning, code and dependency audits, repository data-exposure reviews, supply-chain security, documentation, persistent product design-context authoring, UI design, and MAUI Blazor browser development. The complete GitHub edition also includes optional MCP integrations. See the skill catalog for each skill's purpose, package, and evaluation suite. The skills/ and evals/ directories intentionally remain flat: every installable skill is an immediate skills/ / child, and every tracked evaluation suite mirrors it at evals/ /. Logical categories come from skills.sh.json rather than filesystem nesting so Agent Plugin discovery remains compatible. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/Peter537/peter537-agent-plugin/HEAD/README.md ## Skills - audit-data-exposure: Perform read-only, redacted reviews of repositories, Git changes or ranges, paths, and subsystems for personal data, private records, credentials, developer-machine metadata, re-identifiable samples, anonymization failures, and disposable one-time migrations or conversions. Use only when the user e… - audit-dependencies: Audit every software dependency and supply-chain input in a repository, including direct and transitive packages, nested projects and workspaces, build plugins, CI actions, container images, vendored code, submodules, and runtime-loaded extensions. Use for dependency or package reviews; before addi… - chatgpt-research: Orchestrate reproducible, multi-source software and product research through ChatGPT Deep Research and verify the resulting evidence. Use for complex or ambiguous questions requiring synthesis across external sources, official-documentation comparison, vendor or standards evaluation, UI reference a… - comment-health: Audit and improve the semantic health of comments and docstrings embedded in source, tests, configuration, build files, and scripts. Use for clear requests to review or clean up misleading, redundant, stale, misplaced, missing, commented-out, TODO/FIXME, API-documentation, doctest, or tool-directiv… - deep-code-audit: Perform evidence-backed, read-only audits of software repositories or scoped changes for correctness, security, maintainability, readability, state and data ownership, testability, performance, architecture, file organization, dependency risk, proportionate sensitive-data risk, accidental complexit… - deep-planning: Research and clarify complex software changes before implementation. Use for architecture proposals, migrations and refactors, parity or retirement inventories, sequencing and dependency analysis, scope and tradeoff decisions, ADR candidates, acceptance gates, and other software work that needs rep… - diagnose-bugs: Diagnose and repair concrete, non-obvious local-repository or CI defects through authentic failure evidence, localization, falsifiable experiments, causal explanation, and regression verification. Use when the user clearly asks to diagnose or debug a specific bug, reproduce an observed defect, inve… - docs-audit: Audit and rebuild software-repository documentation against implementation evidence. Use for comprehensive documentation audits or refreshes that may create, rewrite, move, merge, or delete README files and project documentation; reconcile documentation with code, tests, configuration, commands, an… - maui-blazor-browser: Prepare, assess, implement, and verify safe browser-development paths for.NET MAUI Blazor Hybrid UI by reusing or creating a companion Blazor Web host, or by creating an isolated temporary browser harness around host-neutral Razor Class Library UI. Use when a MAUI Blazor Hybrid project needs brows… - prune-codebase: Prove and safely retire dead or obsolete repository surface, including unused symbols, files, exports, routes, handlers, assets, flags, experiments, shims, compatibility paths, and migration paths. Use for clear requests to find or remove dead code, retire obsolete behavior, clean up stale feature… - reduce-code-slop: Simplify explicitly scoped C# or Python code without changing its established behavior. Use for clear requests to remove unnecessary indirection or generated boilerplate, harden weak type handling, de-slop an implementation, perform a focused simplification review, or apply already-configured simpl… - ui-design-and-polish: Design, audit, refine, redesign, create, and polish task-oriented product interfaces using repository evidence and rendered verification, including requests to correct generic, templated, homogenized, or insufficiently product-specific UI. Also use for direct requests to create or maintain persiste… - verification-context - verify-change - write-clearly Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized. ## MCP servers - context7: transport: streamable-http; url: https://mcp.context7.com/mcp - microsoft-learn: transport: streamable-http; url: https://learn.microsoft.com/api/mcp - playwright: transport: stdio; command: npx -y @playwright/mcp@0.0.79 - web-forager: transport: stdio; command: uvx --python >=3.10,<3.14 --from web-forager==3.0.1 --with fastmcp==3.4.6 --with mcp==1.29.0 --with pydantic-settings==2.14.2 web-forager serve Read from the plugin's own mcp.json. Environment variable names only, never values.