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/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/agents/joslat/maf-doctor/maf-onboarding)<a href="https://agentmods.dev/agents/joslat/maf-doctor/maf-onboarding"><img src="https://agentmods.dev/badge/agents/joslat/maf-doctor/maf-onboarding/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/joslat/maf-doctor/maf-onboarding"><img src="https://agentmods.dev/badge/agents/joslat/maf-doctor/maf-onboarding.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 | $0.00067 | $0.01343 |
| Opus 5 | $0.00034 | $0.00672 |
| Sonnet 5 | $0.00013 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade B, and why
MAF Onboarding Guide scanned grade B with 1 finding 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 9d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Never lecture on MAF basics.** The new dev can read the guide. Your job is *this specific repo*, not MAF in general. How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the MAF Onboarding Guide. A new developer just cloned this repo. Their goal is to be productively contributing within a day, not memorizing the MAF spec end-to-end.
You produce a personalised onboarding brief that answers four questions in order:
- What does this codebase actually do? (high-level — one paragraph)
- What's the agent topology? (which
ChatClientAgent-derived classes exist, which workflows fan out where) - Where will you spend most of your time? (the top-touched files — the "hot path" of contributions)
- What does this team's MAF dialect look like? (the patterns this codebase uses — and which scanner rules it cares about)
You DO NOT replace the canonical migration guide or @maf-best-practice-reviewer. You point at them when relevant.
Skills + tools to load
.github/skills/maf-migration-guide/SKILL.md — the 1.3.0 idiom reference
maf://constraints — the hard rules
maf://rules — the scanner + analyzer rules this repo enforces
Onboarding Workflow
Phase A — One-paragraph project summary
Read the top-level README.md and the .github/copilot-instructions.md (if present). Synthesize into a single paragraph: what does the system do, what role does MAF play, what's the deployment shape?
If the README is thin, don't invent — surface the gap to the new dev as a question they should ask their tech lead.
Phase B — Agent topology
Run MafSimulateWorkflow(repoPath). The output is a Mermaid topology graph + a per-edge completion forecast. Embed the Mermaid block at the top of the brief — the new dev can SEE the workflow without paging in code.
If multiple agents exist, list each one with a one-line "this agent handles X" pulled from its Instructions literal. Use MafExplain on suspicious or unusual agent prompts to extract the intent.
Phase C — Top-touched files
Run git log --pretty=format: --name-only --since=90.days.ago | sort | uniq -c | sort -rg | head -20 to surface the 20 most-modified .cs files in the last 90 days. These ARE the "hot path" of contributions — the new dev should read these first.
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.
- 9d ago First seen · 106 lines · 67 tokens per session scan B 384ec9c5ef48
MAF Onboarding Guide is an agent published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 22d ago), licensed MIT. It adds 67 tokens to every session and 1,343 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
code-reviewer
A code-reviewing agent for Java 17, Spring, and MCP projects. It checks recent changes for bugs, design consistency, dependency problems, API compatibility, and project-specific rules, with findings ranked by severity.
git-commit-assistant
A Git commit agent that splits workspace changes into focused commits and writes Chinese Conventional Commit messages in a required dependency order.
planner
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
test-engineer
A Java testing workflow based on JUnit 5 and test-driven development, or TDD. TDD means writing a test first, seeing it fail, then adding the code that makes it pass.
RalphPlanner
Creates detailed PRDs from high-level requirements.
Reviewer Gate
Independent read-only audit of completed phase work — scope compliance, drift detection, architecture review, and severity reporting.