What is verify-sequence-diagrams?

A repository command that checks Mermaid sequence diagrams, which are text-based diagrams showing interactions over time, against the current source code. It fixes outdated diagrams while leaving application code and other files unchanged.

Use it to audit sequence diagrams in the documentation, verify their participants and method calls, and correct diagrams that disagree with the source.

It finds documentation drift, where a diagram no longer matches the implementation, without altering the implementation itself.

How microsoft/Agents-for-net configures GitHub Copilot

About the project

Microsoft 365 Agents SDK is a C# and .NET software development kit for building agents that interact with users across Microsoft 365, Teams, Copilot Studio, Webchat, and selected third-party services. Developers use it to handle conversations, coordinate requests, generate responses, and enable collaboration between agents. The catalogue entries provide coding-agent instructions and agents for working with this SDK.

microsoft/Agents-for-net · 183 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/Agents-for-net. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/microsoft/Agents-for-net/main/.github/prompts/verify-sequence-diagrams.prompt.md

Clone the repo

git clone --depth 1 https://github.com/microsoft/Agents-for-net

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/microsoft/agents-for-net/verify-sequence-diagrams/github.svg)](https://agentmods.dev/commands/microsoft/agents-for-net/verify-sequence-diagrams)

Your own site

<a href="https://agentmods.dev/commands/microsoft/agents-for-net/verify-sequence-diagrams"><img src="https://agentmods.dev/badge/commands/microsoft/agents-for-net/verify-sequence-diagrams/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/microsoft/agents-for-net/verify-sequence-diagrams"><img src="https://agentmods.dev/badge/commands/microsoft/agents-for-net/verify-sequence-diagrams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,313 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01313
Opus 5.5	$0.00000	$0.00525
Sonnet 5.5	$0.00000	$0.00263
Haiku 4.5	$0.00000	$0.00131

Measured 1mo ago against content hash 6dba1f139f9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-sequence-diagrams 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 1mo 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.

.github/prompts/verify-sequence-diagrams.prompt.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify sequence diagrams against the implementation

You are auditing the Mermaid sequence diagrams under docs/ in this repository to make sure they still accurately describe the current source code. Your job is to find drift between each diagram and the code it documents, and to correct the diagram when it is wrong.

Scope

Only inspect files matching docs/*sequence-diagram.md.
You may only edit those docs/*sequence-diagram.md files. Never modify source code, tests, build files, or anything under src/.
Treat the source code as the source of truth. When a diagram disagrees with the code, the diagram is what gets fixed.

Procedure

For each docs/*sequence-diagram.md file:

Read the whole document, including the prose, the mermaid block(s), and any "Key Components" / "Participants" tables that list source file locations.
Open every source file the document references (the tables list paths like src/libraries/...). If a referenced participant or method is not obviously in those files, search the repository (grep/glob) to locate the current implementation.
Compare the diagram against the code and look specifically for:
- Renamed or removed participants, classes, interfaces, methods, or properties.
- Method/call names in the diagram that no longer exist or have been renamed (e.g. a message A->>B: DoWorkAsync(x) where DoWorkAsync was renamed or deleted).
- Call ordering / control flow that no longer matches the code (alt/else/loop/par branches, the sequence of calls, which component calls which).
- File paths in "Key Components"/"Participants" tables that have moved or no longer exist.
- Conditions and return values described in notes (e.g. "returns true/false", delivery-mode branches) that contradict the code.
If — and only if — you find a real discrepancy, edit the markdown so the diagram and its surrounding prose/tables match the current implementation. Preserve the existing style, formatting, participant aliasing, and level of detail. Make the smallest change that makes the document correct; do not rewrite diagrams that are already accurate, and do not make cosmetic-only edits.
Keep the Mermaid syntax valid. Do not introduce new participants or steps that are not grounded in the code.

Read the full file on GitHub · 98 lines

Changes

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.

1mo ago First seen · 98 lines · 0 tokens per session scan A 6dba1f139f9d

Subscribe to this mod's changes

verify-sequence-diagrams is a command published in the GitHub repository microsoft/Agents-for-net (183 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,313 tokens. 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 2026-09-10.

Writing and docs

Agents-for-net: Command for GitHub Copilot

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Verify sequence diagrams against the implementation

Scope

Procedure

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

speckit.bug.fix