What is epoch-subagent-loop?

A workflow for implementing a series of documentation changes with helper agents. Each change is implemented, built and tested, reviewed, fixed if needed, committed, and only then followed by the next change.

Use it for documentation work divided into named epochs, or stages. It coordinates implementation agents, a separate reviewer, build and test checks, and limited fix rounds.

It gives multi-step documentation work a repeatable order and review loop. It prevents the next step from starting before the current one is committed and verified.

How VuDZ/RoslynMcpServer configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to VuDZ/RoslynMcpServer. 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/VuDZ/RoslynMcpServer/main/.agents/skills/epoch-subagent-loop/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/VuDZ/RoslynMcpServer

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vudz/roslynmcpserver/epoch-subagent-loop/github.svg)](https://agentmods.dev/skills/vudz/roslynmcpserver/epoch-subagent-loop)

Your own site

<a href="https://agentmods.dev/skills/vudz/roslynmcpserver/epoch-subagent-loop"><img src="https://agentmods.dev/badge/skills/vudz/roslynmcpserver/epoch-subagent-loop/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vudz/roslynmcpserver/epoch-subagent-loop"><img src="https://agentmods.dev/badge/skills/vudz/roslynmcpserver/epoch-subagent-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,034 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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.01034
Opus 5.5	$0.00031	$0.00414
Sonnet 5.5	$0.00016	$0.00207
Haiku 4.5	$0.00008	$0.00103

Measured 1mo ago against content hash ad7d37c8a526, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

epoch-subagent-loop 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 1mo 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.

.agents/skills/epoch-subagent-loop/SKILL.md · 66 lines

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.

Epoch subagent loop

запуск задачи сабагентом, ревью изменений, если нужны доработки - исправление тем же сабагентом-исполнителем, опять проверка, если нужны доработки - повторить фикс/ревью и так до завершения, потом коммит и следующая эпоха, если указано

The parent orchestrates. It does not implement the epoch itself. One implementer identity per epoch: every fix round resumes that same subagent. Only the reviewer is new each round.

Order

Read the series README. Take the first epoch whose status is not done. Do not start the next epoch until the previous one is committed. The series README wins if it says the epochs share files.
Launch one generalPurpose subagent (run_in_background: false). The prompt must include the epoch file path, the repo root, and every constraint below. The subagent has no chat history. Record its agent id: steps 4 and 7 resume this same subagent.
Parent runs the build and the tests the epoch names, via Roslyn MCP (run_dotnet_build, run_specific_test). No shell dotnet build / dotnet test.
If the build or tests fail, resume the same implementer (never a new one) with the failure text. Repeat until green, at most 3 build-fix rounds. Then stop and report.
Launch a new generalPurpose reviewer (do not resume the implementer). It reads the epoch spec and the diff of files this epoch touched. Pre-existing dirty files are out of scope.
The reviewer returns ACCEPT or a must-fix list. Nits are not must-fix. Spec violations, missing tests, and behavior bugs are must-fix.
If must-fix: resume the implementer (the same subagent, never a new one) with that list only, re-run the tests, then a fresh reviewer. Repeat until ACCEPT, at most 4 review rounds. Then stop and report.
Commit only this epoch's files. Do not commit unrelated dirty files. Do not push.
If the series README lists a later epoch, go back to step 2.

Fix ownership

One implementer per epoch. The subagent launched in step 2 owns every fix round of that epoch: build failures (step 4) and review must-fix (step 7) both resume that subagent, by its id. Never launch a new implementer to apply fixes.

Read the full file on GitHub · 66 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.

1mo ago Changed · +10 lines · +3 tokens per session ad7d37c8a526
1mo ago First seen · 56 lines · 75 tokens per session scan A 65a9e6bfe58c

Subscribe to this mod's changes

epoch-subagent-loop is a skill published in the GitHub repository VuDZ/RoslynMcpServer (8 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,034 once invoked, about $0.0003 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 2026-09-22.

Building agents C# and .NET LLM Writing and docs ai-agent cursor dotnet mcp

csharp-expert

Expert-level C# development with .NET 8+, ASP.NET Core, LINQ, async/await, and enterprise patterns. Use when the user mentions C#, .NET, ASP.NET, enterprise, or Microsoft platforms, or when the task involves Modern C#, Async/Await, LINQ, or ASP.NET Core.

personamanagmentlayer/pcl · 70 tokens

.NET Testing Patterns

.NET testing with xUnit, NUnit, MSTest, FluentAssertions, Moq, integration testing with WebApplicationFactory, and Entity Framework testing.

PramodDutta/qaskills · 33 tokens

opentelemetry-net-instrumentation

Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.

Aaronontheweb/dotnet-skills · 56 tokens

mcp

Build or consume Model Context Protocol (MCP) servers and clients in .NET using the official MCP C# SDK, including stdio, Streamable HTTP, tools, prompts, resources, and capability negotiation. USE FOR: .NET MCP servers or clients; stdio versus HTTP transport choices; tools, resources, prompts, completions, and…

managedcode/dotnet-skills · 123 tokens

semantic-kernel

Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable. USE FOR: adding AI-driven prompts, plugins, or orchestration to a .NET app; reviewing kernel construction, service registration, or plugin usage; building…

managedcode/dotnet-skills · 116 tokens

winforms

Build, maintain, or modernize Windows Forms applications with practical guidance on designer-driven UI, event handling, data binding, MVP separation, and migration to modern .NET. USE FOR: working on Windows Forms UI, event-driven workflows, or classic LOB applications; migrating WinForms from .NET Framework to modern…

managedcode/dotnet-skills · 122 tokens

RoslynMcpServer: Skill for Claude Code