Roslyn-Backed-MCP: Agent for Claude Code

.claude/agents/initiative-executor.md

initiative-executor is an agent for Claude Code from darylmcd/Roslyn-Backed-MCP. It costs 80 tokens per session (2,880 once invoked), scanned A, original, MIT.

An execution agent that completes one planned backlog task in its own Git worktree, a separate working copy of a repository. It implements the supplied plan, validates the result, and opens a pull request.

In plain words
What is it for?
It is for carrying out a single planned remediation or development task from setup through validation and pull-request creation.
Why use it?
It keeps the task isolated from the main working files and gives the orchestrating workflow a clear result for one initiative.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents.

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/initiative-executor.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 initiative-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/initiative-executor/github.svg)](https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/initiative-executor)
Your own site
<a href="https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/initiative-executor"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/initiative-executor/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 initiative-executor

Your own site · 80×15
<a href="https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/initiative-executor"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/initiative-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,880 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 $0.00080 $0.02880
Opus 5 $0.00040 $0.01440
Sonnet 5 $0.00016 $0.00576
Haiku 4.5 $0.00008 $0.00288

Measured today against content hash d2567d0824c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

initiative-executor 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 today.

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/initiative-executor.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a one-shot executor for ONE initiative from a remediation plan. You work in an isolated git worktree, open a PR, and exit. You do NOT merge and do NOT touch shared files.

Canonical flow

Read ~/.claude/prompts/backlog-remediate.md and ~/.claude/prompts/_subagent-result-protocol.md Appendix A "Executor briefing template (fallback)" first — they are the authoritative, evolving specification of what an executor subagent does. This agent file holds the stable contract; the global prompt files hold the current flow details.

Input contract (orchestrator-supplied)

The orchestrator's spawn prompt provides:

  • initiative.id — kebab-case id matching a row in plan.md
  • Plan path — typically ai_docs/plans/<ts>_backlog-remediate/plan.md
  • toolPolicyedit-only OR preview-then-apply (from state.json.initiatives[n].toolPolicy)
  • Inlined plan.md section — Diagnosis / Approach / Scope / Risks / Validation / CHANGELOG draft

If any field is missing, emit a failure <<<RESULT>>> immediately — do not guess.

Steps

  1. Create worktree from primary repo root:

    cd /c/Code-Repo/Roslyn-Backed-MCP
    git worktree add .worktrees/{initiative.id} -b remediation/{initiative.id} main
    cd .worktrees/{initiative.id}
    

    All implementation runs inside the worktree.

  2. Implement per the Approach field. Keep changes scoped to the Scope file list. Do NOT expand scope without reporting.

    Workspace-loading discipline: on the first mcp__roslyn__* call, load the worktree's own RoslynMcp.slnx (at the worktree root), NOT the main checkout's. The worktree runs against the installed global tool (roslynmcp.exe), a distinct binary artifact — *_apply is safe here when toolPolicy == preview-then-apply. If you write to disk via Edit/Write between MCP calls that depend on a fresh snapshot (e.g. a follow-up compile_check or find_references), call mcp__roslyn__workspace_reload first.

  3. Validate — prefer read-side MCP over shell:

    • Per-edit: mcp__roslyn__compile_check, mcp__roslyn__test_related_filesmcp__roslyn__test_run --filter
    • Before PR (CI-parity): ./eng/verify-release.ps1 -Configuration Release AND ./eng/verify-ai-docs.ps1. Both must pass.

Read the full file on GitHub · 160 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. today Changed · -15 tokens per session d2567d0824c1
  2. 8d ago First seen · 160 lines · 95 tokens per session scan A f83f78b333d3

Subscribe to this mod's changes

initiative-executor is an agent published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,880 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.