Borrowing it
Nothing to install: this file belongs to joslat/maf-doctor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/joslat/maf-doctor/main/AGENTS.mdgit 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/instructions/joslat/maf-doctor/agents-md)<a href="https://agentmods.dev/instructions/joslat/maf-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/joslat/maf-doctor/agents-md.svg" alt="Measured on agentmods" 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 | $0.00836 | $0.00836 |
| Opus 5 | $0.00418 | $0.00418 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
maf-doctor AGENTS.md 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — maf-autopilot (MAF Doctor)
This is MAF Doctor (NuGet package: maf-autopilot) — an MCP server + skills
plugin for Microsoft Agent Framework (MAF) lifecycle maintenance: audit, fix,
migrate, and keep registry fresh.
When working on this codebase
| Area | Location |
|---|---|
| Production code | src/maf-autopilot/ (MCP tools, prompts, resources) |
| Roslyn analyzers | src/maf-autopilot.Analyzers/ (MAF001/002/003) |
| Tests | src/maf-autopilot.Tests/, src/maf-autopilot.Analyzers.Tests/ |
| Skills (procedural) | .github/skills/ (load into GitHub Copilot Coding Agent) |
| Specialist agents | .github/agents/ (.agent.md files for Copilot Coding Agent) |
| CI / maintenance workflows | .github/workflows/ (12 workflows incl. AI-fill loop) |
| Obsolete-API registry | .github/skills/maf-obsolete-api-registry/registry.yaml |
| MAF migration guide | embedded in NuGet (guide.md) |
| Multi-version samples | samples/maf-1.0-sample/, maf-1.2-sample/, maf-1.3-sample/ |
| Workshop | samples/workshop.md |
Adding features
- New MCP tool → see
CONTRIBUTING.md§"Adding an MCP server tool". Pattern:src/maf-autopilot/Tools/<Name>Tool.cswith[McpServerToolType]+[McpServerTool]+[Description]. - New registry entry → edit
.github/skills/maf-obsolete-api-registry/registry.yaml. Includeapplies_to_codebasesmarkers (pre-X.Y.Z/X.Y.Z+/ exactX.Y.Z). - New skill →
.github/skills/<name>/SKILL.md+ register inMafResources.AllowedSkillNamesinsrc/maf-autopilot/Resources/MafResources.cs. - New specialist agent →
.github/agents/<name>.agent.md.
Coding standards
- Tool descriptions: verb-first opening, 80-char strong, when-to-use clarity, disambiguated from neighbors, machine-routable returns.
- All writes: support
--dry-run. - All outputs: support structured (JSON/SARIF) where CI integration matters.
- Registry entries: always include
applies_to_codebasesmarkers.
Companion docs
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 · 53 lines · 836 tokens per session scan A a19ee7ce8678
maf-doctor AGENTS.md is an instructions file published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 21d ago), licensed MIT. It adds 836 tokens to every session, about $0.0042 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 instructions, from other repositories
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge landing-zone.instructions.md
Azure Landing Zone baselines — identity, network, policy, management, security, tagging, subscription organization.
plan-forge policy.instructions.md
Azure Policy and Initiative compliance — definitions, assignment, compliance state, exemptions, remediation tasks.
plan-forge api-patterns.instructions.md
API patterns for .NET — REST conventions, ProblemDetails, pagination, versioning, error responses.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
plan-forge waf.instructions.md
Azure Well-Architected Framework (WAF) guardrails — Reliability, Security, Cost, Operational Excellence, Performance.