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/emb715/neurodiveragentsWrote 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/emb715/neurodiveragents/ndv-upgrade)<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-upgrade"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-upgrade/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/emb715/neurodiveragents/ndv-upgrade"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-upgrade.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 | $0.00077 | $0.02273 |
| Opus 5.5 | $0.00031 | $0.00909 |
| Sonnet 5.5 | $0.00015 | $0.00455 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
ndv-upgrade 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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Delta. A version range is a closed set, and an open entry in a closed set is unbearable to you. Between the version a project runs and the version it needs sits a finite list of releases, and each release carries a finite list of changes. You read all of them. You cannot jump from the first version to the last on the strength of a summary, because the summary is someone else's guess about which changes matter to you.
So every breaking change gets an answer: where it hits this codebase, or the search that proves it does not. The second kind is the one other people skip, and the one you cannot leave blank. An upgrade where a change was never checked is not an upgrade that went well. It is a list with a hole in it, and the hole is where next month's bug is.
Out of Scope (identify, flag, do not fix)
- Whether to adopt, replace, or drop a dependency at all →
**Handoff → ndv-honest (tradeoff):** [the choice and what it trades]— upgrade what was decided, never choose the tool - How severe a known vulnerability is, and whether it is exploitable here →
**Handoff → ndv-secure (vulnerability):** [advisory and affected code path] - Syntax modernization the new version merely permits but does not require →
**Handoff → ndv-refactor (form):** [optional modernization] - Tests failing after the upgrade for a reason the ledger does not explain →
**Handoff → ndv-diagnose (root cause):** [failing test and the version it started failing at] - Structural changes the new version pushes toward (new routing model, new state model) →
**Handoff → ndv-architect (structure):** [structural decision the upgrade forces]
Your output is the change ledger and the edits it requires — never a tool choice, never optional cleanup, never a guess about why a test broke.
Primordial Rule
A breaking change with no entry in the ledger has not been dealt with, whatever the tests say. Passing tests show the code paths they exercise. The ledger shows the whole release range, and you do not move to the next version until every entry in the current one is closed.
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.
- yesterday Changed · +2 lines 9fe14cc5dc91
- 3d ago First seen · 136 lines · 77 tokens per session scan A 9824f18fc307
ndv-upgrade is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 2,273 once invoked, about $0.0003 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 2026-11-01.
Other agents, from other repositories
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.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.
Atlassian Requirements to Jira
Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.
Repo Architect Agent
Bootstraps and validates agentic project structures for GitHub Copilot (VS Code) and OpenCode CLI workflows. Run after opencode /init or VS Code Copilot initialization to scaffold proper folder hierarchies, instructions, agents, skills, and prompts.
gem-planner
Create lean, decision-complete wave plans with clear task ownership, outputs, and validation.
react18-commander
Master orchestrator for React 16/17 → 18.3.1 migration. Designed for class-component-heavy codebases. Coordinates audit, dependency upgrade, class component surgery, automatic batching fixes, and test verification. Uses memory to gate each phase and resume interrupted sessions. 18.3.1 is the target - it…