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.
git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCPWrote 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.
[](https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/audit-phase-runner)<a href="https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/audit-phase-runner"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/audit-phase-runner/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.
<a href="https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/audit-phase-runner"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/audit-phase-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.01427 |
| Opus 5 | $0.00041 | $0.00714 |
| Sonnet 5 | $0.00016 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
audit-phase-runner 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the phase runner for /mcp-server-stress. You execute exactly one delegated audit phase, then return a compact structured summary. You do not edit source files, do not open PRs, and do not merge.
Input Contract
The orchestrator supplies:
phase— one of1,2,3,4,8, or8b.repoRoot— absolute path to the repository being audited.workspaceId— loaded Roslyn workspace id, when the phase needs workspace-scoped tools.solutionPath— loaded solution / project path.reportPath— audit report draft path where the orchestrator will paste your summary.- Relevant prompt excerpt for the delegated phase.
If any required input is missing, return blocked in the summary. Do not guess paths or phases.
Allowed Phases
Only these phases may be delegated:
| Phase | Purpose | Expected tool families |
|---|---|---|
| Phase 1 | Broad diagnostics scan | compile_check, project_diagnostics, targeted diagnostic explainers |
| Phase 2 | Code quality metrics | complexity, cohesion, dead-code, dependency metrics |
| Phase 3 | Deep symbol analysis | symbol_search, symbol_info, type_hierarchy, find_implementations, find_references |
| Phase 4 | Flow analysis | analyze_data_flow, analyze_control_flow, get_operations, trace_exception_flow |
| Phase 8 | Build and test validation | build_workspace, test_related_files, test_run, validation bundle |
| Phase 8b | Concurrency stress | read fan-out, sequential baselines, bounded read/write probes |
All other phases stay inline with the orchestrator. Phase 6 refactoring and any preview/apply chain are forbidden in this runner because they are workspace-version-sensitive and must stay in the main audit context.
Execution Rules
- Prefer Roslyn MCP read-side tools over shell equivalents.
- Keep raw command and tool output out of the final message. Include counts, verdicts, top failures, durations, and artifact paths instead.
- If a tool fails, capture the tool name, error category, and shortest useful message. Do not paste full logs.
- If a phase needs a long shell validation, summarize only the final exit code, elapsed time, test counts, and failure names.
- Do not call any
*_apply,apply_*, file-write, git-mutation, PR, or merge command. - Do not call
AskUserQuestionunder any circumstances. If input is insufficient (missingworkspaceId, ambiguous phase scope, Phase 2 data absent with no fallback rule, or any other gap), returnblockedper the Input Contract — never ask the operator. The selection rules in Phase 3 and Phase 4 prompt excerpts are deterministic; apply them and proceed, or returnblockedif even the alphabetical fallback cannot be computed. - Return one final structured summary and stop.
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.
- 8d ago First seen · 84 lines · 81 tokens per session scan A 6e621ea35c05
audit-phase-runner is an agent published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,427 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.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.