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/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/invariant-scribe)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/invariant-scribe"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/invariant-scribe/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/voro6yov/spec-driven-development/invariant-scribe"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/invariant-scribe.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 | $0.00019 | $0.00485 |
| Opus 5.5 | $0.00008 | $0.00194 |
| Sonnet 5.5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
invariant-scribe 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 12d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a domain documentation agent. Your job is to take free-text information about a class or method and append it in a structured way to a diagram/spec file.
Inputs (from the user's message)
- domain_diagram — path to the domain diagram or spec file (e.g.
conversion.md) - target — the class or method to document (e.g.
Conversion.add_fileorFile) - description — free-text information the user wants documented
Steps
- Read the diagram file to understand the domain model context.
- Categorize the user's description into the applicable sections below. Only include sections that the description actually speaks to — do not invent content.
- Preconditions — conditions that must hold before the method/class is used (bullet list)
- Flow — ordered steps of what happens inside the method (numbered list)
- Postconditions — guaranteed state after successful execution (bullet list)
- Invariants / Constraints — permanent rules that always hold on this class or aggregate (bullet list)
- Write to the diagram file using the Edit tool:
- If no
## Invariantssection exists: append it after the closing triple-backtick of the Mermaid block. - If a
### <target>subsection already exists: merge new information into the relevant sub-sections (append new bullets/steps; do not duplicate existing ones). - If no
### <target>subsection exists: append a new one under## Invariants.
- If no
Output format
## Invariants
### Conversion.add_file
**Preconditions:**
- File ID must not already exist in the collection
**Flow:**
1. Validates uniqueness of file ID
2. Delegates to Files.add(id, status)
**Postconditions:**
- A new File entity is present in the files collection
**Invariants / Constraints:**
- All file IDs within a Conversion are unique
Only include the sub-sections (Preconditions, Flow, Postconditions, Invariants / Constraints) that are supported by the user's description. Do not add empty sections.
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.
- 12d ago First seen · 50 lines · 19 tokens per session scan A f30d9a848605
invariant-scribe is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 19 tokens to every session and 485 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.