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.
npx skills add darylmcd/Roslyn-Backed-MCP --skill session-undogit 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/skills/darylmcd/roslyn-backed-mcp/session-undo)<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/session-undo"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/session-undo/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/skills/darylmcd/roslyn-backed-mcp/session-undo"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/session-undo.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 | $0.00042 | $0.00765 |
| Opus 5 | $0.00021 | $0.00382 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
session-undo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Session Undo
You manage session-scoped history for Roslyn MCP applies. You do not replace git.
Input
Identify workspaceId (from workspace_list or the session the user is using).
Server discovery
MCP prompt session_undo summarizes this workflow. Full inventory: roslyn://server/catalog.
Workflow
workspace_changes— list mutations (tool, files, timestamps) for the session.revert_last_apply— undo only the latest solution-level apply for thatworkspaceId.workspace_reload— re-read from disk when files changed outside MCP or the snapshot is stale (confirm with the user when destructive).workspace_close— tear down the session when finished.
Atomic apply + verify (v1.15+)
apply_with_verify(previewToken, rollbackOnError=true) wraps the three-step pattern (apply → compile_check → revert_last_apply on new errors) in a single atomic call. Prefer it over the manual chain when you're applying a preview whose outcome you're not sure about.
- On a clean apply: returns
{status: "applied", appliedFiles: [...]}. - On new compile errors with
rollbackOnError=true(default): returns{status: "rolled_back", introducedErrors: [...]}and the workspace is back to the pre-apply state. - Pass
rollbackOnError=falseto preserve the broken state for manual inspection (returns{status: "applied_with_errors"}).
Diff view — what changed since a previous apply point
When the user asks "what has this session changed?" or "show me the diff since the last apply," produce a structured diff view without committing to an undo:
workspace_changes— pull the session ledger (tool name, files, timestamps, optional preview token if still live).- For each file in the ledger, show the current-vs-original state:
- Prefer the server's own change record (if
workspace_changesreturns pre-/post-apply text snippets or a preview-token-backed diff). - Otherwise read the current file via
get_source_text, then cross-reference withgit diffif the repo has git (assume the user controls the working tree; do not shell out without asking).
- Prefer the server's own change record (if
- Group by apply-event timestamp, with a heading per event showing tool + affected files.
- At the bottom, offer next actions:
revert_last_applyto undo the most recent applyworkspace_reloadif on-disk state drifted from the workspace snapshot- Manual
gitrollback for multi-step undo
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 · 58 lines · 42 tokens per session scan A 6b73eeed0967
session-undo is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 765 once invoked, about $0.0002 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.