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 joslat/maf-doctor --skill maf-migration-retrospectivegit clone --depth 1 https://github.com/joslat/maf-doctorWrote 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/joslat/maf-doctor/maf-migration-retrospective)<a href="https://agentmods.dev/skills/joslat/maf-doctor/maf-migration-retrospective"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-migration-retrospective/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/joslat/maf-doctor/maf-migration-retrospective"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-migration-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 111 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00061 | $0.01357 |
| Opus 5 | $0.00030 | $0.00678 |
| Sonnet 5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
maf-migration-retrospective 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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
migration-retrospective
Purpose
Every migration surfaces surprises — patterns the plan didn't predict, docs that were wrong, APIs that behaved differently than expected. This skill captures those surprises systematically and feeds them back into the toolkit's knowledge base.
After 10 migrations, the obsolete-api-registry.yaml covers real-world CS0618 patterns that aren't in any official docs. After 20, the Known Misalignments section becomes the most battle-tested part of the guide. This is the compound effect.
When to Use This Skill
- Immediately after a migration completes (
T11.2 — Done) - Before closing any migration branch or PR
- When a migration hit a surprise that wasn't in the plan
The Retrospective Workflow
Step 1 — Read the completed migration plan
Read src/docs/migration-plan.md — specifically:
- The Notes column of each task row (where surprises were recorded during execution)
- Any tasks with
% Done: 100%that have non-empty notes - The Risk Register section — were any predicted risks wrong or missing?
Step 2 — Read build error history (if available)
If terminal output is available from the migration session:
# Look for unexpected build errors in terminal history
# Focus on: CS0246 errors not predicted by the plan, runtime exceptions, CS0618 not in registry
Key questions:
- Were there CS0246 errors for types/members NOT in the migration plan?
- Were there CS0618 warnings NOT in the registry?
- Were there silent runtime failures detected by smoke tests?
Step 3 — Identify surprises
For each surprise (unexpected error, wrong doc, new pattern):
| Surprise type | Action |
|---|---|
| CS0618 not in registry | Add to registry.yaml |
| CS0246 for type/member not in plan | Add to registry + add to breaking changes table in maf-constraints.instructions.md |
| Official doc was wrong | Add to Known Misalignments in maf-1.3.0-migration-guide.md |
| Silent runtime failure | Add to maf-fan-out-validator skill |
dotnet-inspect missed something |
Note in dotnet-inspect/SKILL.md limitations section |
| New hard constraint discovered | Add to maf-constraints.instructions.md Hard Constraints section |
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.
- 12d ago First seen · 156 lines · 61 tokens per session scan A 0c07e6a7e432
maf-migration-retrospective is a skill published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 25d ago), licensed MIT. It adds 61 tokens to every session and 1,357 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
winui-setup
Install and verify the prerequisites the win-dev-skills WinUI 3 toolchain depends on — .NET SDK 8.0.100+, WinApp CLI 0.6+, and Developer Mode. Use only when the user explicitly asks to set up or repair the toolchain. Do not invoke automatically when another skill reports a missing prerequisite; tell the user what is…
winui-wpf-migration
Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and…
migrate-mstest-v3-to-v4
Use this skill before answering, planning, or editing any MSTest 3.x-to-4.x upgrade or post-upgrade failure. Triggers include "MSTest v4 breaking changes"; CS0507/CS0103/CS1061/CS1615; ExecuteAsync, CallerInfo, DisplayName, or custom TestMethodAttribute; ClassCleanupBehavior; ContainsKey; ThrowsExactly or…
wpf
Build and modernize WPF applications on .NET with correct XAML, data binding, commands, threading, styling, and Windows desktop migration decisions. USE FOR: working on WPF UI, MVVM, binding, commands, or desktop modernization; migrating WPF from .NET Framework to .NET; integrating newer Windows capabilities into a…
worker-services
Build long-running .NET background services with BackgroundService, Generic Host, graceful shutdown, configuration, logging, and deployment patterns suited to workers and daemons. USE FOR: background services; scheduled workers; hosted services; worker extraction; graceful shutdown, health checks, and service hosting…
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…