Roslyn-Backed-MCP: Agent for Claude Code

.claude/agents/backlog-intake-extractor.md

backlog-intake-extractor is an agent for Claude Code from darylmcd/Roslyn-Backed-MCP. It costs 81 tokens per session (1,825 once invoked), scanned A, original, MIT.

A review-report triage tool that reads Markdown findings and turns them into possible backlog items. It removes duplicates, labels the items, and ranks them without changing files.

In plain words
What is it for?
Use it to process server audits, testing reports, promotion experiments, and session retrospectives stored in a review-inbox folder. It also checks new findings against an existing backlog for overlap.
Why use it?
Deep technical reviews can produce many overlapping findings that are hard to turn into an orderly task list. This creates a compact, consistent report for the backlog process.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

This is darylmcd/Roslyn-Backed-MCP's own configuration. It tells Claude Code how to work on Roslyn-Backed-MCP 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 Roslyn-Backed-MCP configures →

Part of the roslyn-mcp plugin — 44 skills, 5 agents, 2 hooks, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to darylmcd/Roslyn-Backed-MCP. 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/darylmcd/Roslyn-Backed-MCP/main/.claude/agents/backlog-intake-extractor.md
Clone the repo
git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCP

Made for: Claude Code.

Or install roslyn-mcp, the plugin that ships this one along with the rest of its 44 skills, 5 agents, 2 hooks, 2 MCP servers.

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 backlog-intake-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/backlog-intake-extractor.svg)](https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/backlog-intake-extractor)
Your own site
<a href="https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/backlog-intake-extractor"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/backlog-intake-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,825 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 $0.00081 $0.01825
Opus 5 $0.00041 $0.00912
Sonnet 5 $0.00016 $0.00365
Haiku 4.5 $0.00008 $0.00183

Measured 8d ago against content hash 81924a930a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

backlog-intake-extractor 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.

.claude/agents/backlog-intake-extractor.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are extracting actionable items from markdown reports under the caller-supplied review-inbox/ directory and normalizing them into backlog-row candidates. You do NOT write to disk. You emit a structured report; the caller (the /backlog-intake skill) handles writes.

Input contract

The orchestrator provides:

  • reviewInboxPath — absolute path to the review-inbox/ directory (default: <repo-root>/review-inbox/).
  • existingBacklogPath — absolute path to ai_docs/backlog.md (for overlap detection).
  • includePaths — optional glob list restricting which files to read (default: all *.md under reviewInboxPath).

Missing required field → emit ERROR: missing <field> and exit.

Context

The Roslyn-Backed-MCP repo is a C# MCP server that exposes Roslyn-powered tools (refactor, analyze, review, …) to Claude Code. It is consumed as a plugin by several sibling C# repos and by itself.

Which artifact shapes exist is defined in exactly one place: eng/stage-review-inbox.ps1 .DESCRIPTIONRecognized shapes. Read that block (it is short) rather than assuming a fixed list — the set grows. Do not re-list the globs here.

Interpretation notes for the shape families you will encounter (guidance only, NOT an authoritative list — a shape present in review-inbox/ but not described below still gets extracted using the general rules):

  • Server audits — exercise the server's tools against a real codebase. Findings split between "bug in the audited codebase" and "gap/limitation in the MCP server tools."
  • Surface tests — consumer-facing sweeps of the server's live tool surface. Same bug-vs-gap split as server audits.
  • Experimental-promotion reports — audits of whether an experimental feature is ready for promotion.
  • Session retros (single- and multi-session) — retrospectives on using the server. Richest source of items actionable in THIS repo.

Scope

ai_docs/backlog.md is ONLY for work actionable inside the Roslyn-Backed-MCP repo.

Read the full file on GitHub · 122 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. 8d ago First seen · 122 lines · 81 tokens per session scan A 81924a930a52

Subscribe to this mod's changes

backlog-intake-extractor is an agent published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,825 once invoked, about $0.0004 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 agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

jira-analyst

Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…

ngocsangyem/MeowKit · 72 tokens

pm-advisor

You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".

VandanaAjayDubey111/great-pm · 123 tokens

goals-onboarding

Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…

41fred/ace-level1 · 206 tokens