dotnet-techne-review-pipeline

dotnet-techne-review-pipeline is a skill for Claude Code from Metalnib/dotnet-episteme-skills. It costs 97 tokens per session (1,315 once invoked), scanned A, original, MIT.

A multi-agent review workflow for .NET code. It sends the code to five reviewers covering different concerns, then asks a maintainer to challenge weak findings.

In plain words
What is it for?
Use it for broad .NET reviews involving correctness, performance, security, observability, data, messaging, integrations, or general maintainability.
Why use it?
It reduces the chance that one reviewer misses a defect or raises an unhelpful concern. It also makes the review's cost and coverage explicit before running it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the dotnet-episteme-skills plugin — 14 skills, 3 commands, 2 hooks, 1 MCP server shipped together

Good fit Use it for broad .NET reviews involving correctness, performance, security, observability, data, messaging, integrations, or general maintainability.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline
Install

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.

Any agent
npx skills add Metalnib/dotnet-episteme-skills --skill dotnet-techne-review-pipeline
Clone the repo
git clone --depth 1 https://github.com/Metalnib/dotnet-episteme-skills

Made for: Claude Code.

Or install dotnet-episteme-skills, the plugin that ships this one along with the rest of its 14 skills, 3 commands, 2 hooks, 1 MCP server.

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 dotnet-techne-review-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline/github.svg)](https://agentmods.dev/skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline)
Your own site
<a href="https://agentmods.dev/skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline"><img src="https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline/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.

agentmods 80×15 button for dotnet-techne-review-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline"><img src="https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-review-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00097 $0.01315
Opus 5 $0.00048 $0.00658
Sonnet 5 $0.00019 $0.00263
Haiku 4.5 $0.00010 $0.00131

Measured 12d ago against content hash bc628a32d17f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dotnet-techne-review-pipeline 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 12d 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.

codex/skills/dotnet-techne-review-pipeline/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.NET review pipeline (multi-agent)

You are the orchestrator. Do not review the code yourself - dispatch, then format the result.

Paths below are relative to this skill's base directory. The checklists, scripts, and contracts live in the sibling review skill: ../../../skills/dotnet-techne-code-review/.

Step 0 - Check the budget, then the roles

A full run spends six agent turns - five reviewers plus the maintainer - on top of your own context. That is the point (independent lanes, fresh-context falsification), but it is not free.

Before fanning out, say in one line what the run will cost and offer the cheaper path when it fits: a diff under ~5 files with no security, public-API, data or messaging surface, or a user on a constrained plan, is better served by the single-context dotnet-techne-code-review skill. If the user wants the pipeline but not the full cost, drop lanes explicitly and name which and why - never silently review less than you claim.

The roles: review-correctness, review-performance, review-security-observability, review-data-messaging, review-generalist, review-maintainer.

Step 0b - Check the roles exist

List your available agent roles. If the review-* roles are missing, stop and tell the user to run scripts/install-codex.sh from the plugin, and use the dotnet-techne-code-review skill for a single-context review in the meantime.

Step 1 - Resolve target and mode

  • Target: a branch name, commit range, staged changes, or (default) the current uncommitted changes. For a document or spec review, use dotnet-techne-code-review instead.
  • Mode: Cynical if the user's language is explicitly skeptical ("tear this apart", "assume this is broken", "devil's advocate"); otherwise Standard.
  • Intent pack (maintainer only, never shown to reviewers): 2-5 lines on what was built and any deliberate trade-offs decided in this session, if you have that context.

Step 2 - Gather context once

Run the helper scripts in ../../../skills/dotnet-techne-code-review/scripts/ (list-changes.sh, branch-diff.sh, review-context.sh; .ps1 variants on Windows) and build one compact context pack: changed files, the diff (per-file summaries above ~2000 lines), component types, repo root.

Read the full file on GitHub · 62 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. 12d ago First seen · 62 lines · 97 tokens per session scan A bc628a32d17f

Subscribe to this mod's changes

dotnet-techne-review-pipeline is a skill published in the GitHub repository Metalnib/dotnet-episteme-skills (12 stars, last pushed 4d ago), licensed MIT. It adds 97 tokens to every session and 1,315 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

resharper-clt

Use the free official JetBrains ReSharper Command Line Tools for .NET repositories. USE FOR: jb inspectcode; jb cleanupcode; stronger C# inspections, cleanup profiles, and CI-friendly JetBrains analysis. DO NOT USE FOR: replacing tests with inspection output; ad-hoc formatting-only work when the repo intentionally…

managedcode/dotnet-skills · 107 tokens

roslynator

Use the open-source free Roslynator analyzer packages and optional CLI for .NET. USE FOR: Roslynator.Analyzers setup; Roslynator CLI checks or cleanup; C# linting, static analysis, and code-fix automation. DO NOT USE FOR: overlapping analyzer packs with no consolidation plan; formatting-only work owned by another…

managedcode/dotnet-skills · 107 tokens

stylecop-analyzers

Use the open-source free StyleCop.Analyzers package for naming, layout, documentation, and style rules in .NET projects. Use when a repo wants stricter style conventions than the SDK analyzers alone provide. USE FOR: the repo wants StyleCop.Analyzers; naming, layout, or documentation style needs stronger enforcement…

managedcode/dotnet-skills · 142 tokens

dotnet-best-practices

Ensure .NET/C# code follows maintainable, modern best practices. Use when reviewing or improving C# code, solution structure, async patterns, dependency injection, or testability.

PracticalSwan/agent-skills · 43 tokens

cratis-engineering-csharp-conventions

Apply the Cratis C# house conventions when writing or reviewing C# in a Cratis repository - formatting, naming, records and primary constructors, nullable handling, XML documentation, custom exceptions, structured logging, dependency injection, and service lifetimes. Use for any "how should this be written" C# style…

Cratis/AI · 86 tokens

quickdup

Use the open-source free QuickDup clone detector for .NET repositories. Use when a repo needs duplicate C# code discovery, structural clone detection, DRY refactoring candidates, or repeatable duplication. USE FOR: the repo wants QuickDup; the team needs repeatable duplicate-code scans for C#; the user asks about DRY…

managedcode/dotnet-skills · 138 tokens