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-doctor-self-evolutiongit 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-doctor-self-evolution)<a href="https://agentmods.dev/skills/joslat/maf-doctor/maf-doctor-self-evolution"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-doctor-self-evolution/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-doctor-self-evolution"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-doctor-self-evolution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Rogue Agent · line 188 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Data Exfiltration · line 29 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Memory Poisoning · line 135 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00090 | $0.02280 |
| Opus 5 | $0.00045 | $0.01140 |
| Sonnet 5 | $0.00018 | $0.00456 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
maf-doctor-self-evolution 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 11d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maf-doctor-self-evolution
Purpose
When Microsoft ships a new MAF release, maf-autopilot must evolve to track it:
.maf-version, the compatibility matrix, per-version migration guides, and the
obsolete-API registry all need updating. Most of the work is automated — your job
as maintainer is to trigger the right workflow, review the PR, and merge it.
This skill is the step-by-step operator runbook. For a description of what the
pipeline does internally, see the maf-release-watcher skill.
Pre-flight — is an update actually needed?
Run these checks before touching anything:
# 1. What version is the toolkit currently tracking?
Get-Content .maf-version # should be the last known-good MAF version
# 2. What is the latest STABLE MAF version on NuGet?
$raw = Invoke-RestMethod "https://api.nuget.org/v3-flatcontainer/microsoft.agents.ai/index.json"
$raw.versions | Where-Object { $_ -notmatch '-(alpha|beta|rc|preview)' } | Select-Object -Last 3
# 3. Is there already an open PR or issue for the new version?
gh issue list --label maf-release --repo joslat/maf-doctor
gh pr list --base main --repo joslat/maf-doctor
If .maf-version matches the latest stable on NuGet → nothing to do.
If .maf-version is behind → proceed.
Step 1 — Trigger the release watcher
gh workflow run maf-release-watcher.yml \
--repo joslat/maf-doctor \
-f maf_version=X.Y.Z
Replace X.Y.Z with the new MAF version (e.g. 1.13.0).
Leave maf_version blank to have the watcher auto-detect the latest NuGet stable:
gh workflow run maf-release-watcher.yml --repo joslat/maf-doctor
Cron note: the watcher also runs every Thursday at 06:00 UTC (
0 6 * * 4). If a release landed mid-week you can trigger manually rather than waiting.
Step 2 — Watch the run
# List the most recent watcher runs
gh run list --workflow maf-release-watcher.yml \
--repo joslat/maf-doctor --limit 5
# Tail the live log of the most recent run
gh run watch --repo joslat/maf-doctor
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.
- 11d ago First seen · 226 lines · 90 tokens per session scan A 6118aef779d5
maf-doctor-self-evolution is a skill published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 24d ago), licensed MIT. It adds 90 tokens to every session and 2,280 once invoked, about $0.0005 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-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…
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…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
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…