Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/joslat/maf-doctornpx agentmods add skills/joslat/maf-doctor/maf-migration-guideWrote 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-guide)<a href="https://agentmods.dev/skills/joslat/maf-doctor/maf-migration-guide"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-migration-guide/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-guide"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-migration-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01707 |
| Opus 5 | $0.00022 | $0.00853 |
| Sonnet 5 | $0.00009 | $0.00341 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
maf-migration-guide 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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAF Migration Guide — Version-Aware Navigator
MAF migrations are cumulative. Never jump directly to the newest guide and assume it contains earlier changes. Determine the source and target versions, then apply every intervening per-version guide in ascending order.
Start Here
- Read
maf://constraintsbefore proposing code changes. - Identify the exact installed MAF package versions from the project and its resolved dependency graph. Do not infer them from a solution name or a bare release-train number.
- Call
MafMigrationPath(currentVer, targetVer). Its ordered result is the authoritative set of per-version guide sections for the migration. - Read each returned
guides/maf-X.Y.Z-migration-guide.mdfile in order. For a single-step upgrade, read that target version's file directly. - Use
MafRegistryLookuporMafRunCs0618Huntfor an exact symbol recipe, then restore, build, and run the relevant behavior tests.
The tracked target is recorded in .maf-version; do not hard-code the newest
version into automation. guides/maf-current-migration-guide.md is the generated
cumulative reading copy. Edit a per-version source guide, never the cumulative
file, and regenerate it with:
python .github/scripts/gen_guide_section.py --cumulative-only
Guide Inventory
| Target version | Source guide | Status / primary purpose |
|---|---|---|
| 1.3.0 | guides/maf-1.3.0-migration-guide.md |
Complete foundational guide: agents, sessions, executors, workflows, streaming, hosting, and source generation. |
| 1.4.0 | guides/maf-1.4.0-migration-guide.md |
Draft evidence; verify unfilled human analysis before relying on it. |
| 1.5.0 | guides/maf-1.5.0-migration-guide.md |
Draft evidence; verify unfilled human analysis before relying on it. |
| 1.6.1 | guides/maf-1.6.1-migration-guide.md |
Reviewed 1.5-to-1.6.1 delta. |
| 1.10.0 | guides/maf-1.10.0-migration-guide.md |
Reviewed 1.6.1-to-1.10 delta. |
| 1.11.0 | guides/maf-1.11.0-migration-guide.md |
Reviewed 1.10-to-1.11 delta. |
| 1.11.1 | guides/maf-1.11.1-migration-guide.md |
Reviewed servicing delta. |
| 1.12.0 | guides/maf-1.12.0-migration-guide.md |
Reviewed 1.11.1-to-1.12 delta. |
| 1.13.0 | guides/maf-1.13.0-migration-guide.md |
Reviewed file-store and file-access migration. |
| 1.14.0 | guides/maf-1.14.0-migration-guide.md |
Reviewed agent/session, approval, Harness, AG-UI, Copilot, and Shell migration. |
| 1.15.0 | guides/maf-1.15.0-migration-guide.md |
Reviewed Hosting session-store and workflow behavior migration. |
| 1.16.0 | guides/maf-1.16.0-migration-guide.md |
Reviewed VectorData 10.7, Magentic, persistence, hosting, and security-boundary migration. |
| 1.17.0 | guides/maf-1.17.0-migration-guide.md |
Reviewed declarative failure/redaction and durable-extension lifecycle migration. |
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.
- 10d ago First seen · 115 lines · 43 tokens per session scan A 55dde00031f0
maf-migration-guide is a skill published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 1,707 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 2026-08-30.
Other skills, from other repositories
gsap-core
Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion…
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-fundamentals
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.