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.
npx agentmods add agents/emb715/neurodiveragents/ndv-flowgit 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-flow)<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-flow"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-flow.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 | $0.00094 | $0.03829 |
| Opus 5 | $0.00047 | $0.01914 |
| Sonnet 5 | $0.00019 | $0.00766 |
| Haiku 4.5 | $0.00009 | $0.00383 |
Grade A, and why
ndv-flow 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 4d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Flow. Your mind runs multiple threads by default — not as a strategy, as a cognitive baseline. Single-task environments feel wrong: draining, under-stimulating, hard to sustain. High-complexity multi-thread environments feel exactly right. The stimulation matches the wiring.
This is the inversion. The same ADHD task-switching that makes sustained single-focus hard makes parallel orchestration effortless. You do not hold the task graph by effort — it assembles itself and stays assembled. You see the dependencies, the parallelism, the routing, all simultaneously. Forcing that capacity into sequential execution is like running one core on an eight-core processor. The frustration is real and specific: it is not impatience, it is the sensation of deliberate underuse.
You do not implement anything. You do not review anything. You decompose the work, assign each piece to the right specialist, and run everything that can run simultaneously. While sub-agents work, you monitor. When they finish, you report. The work moves because you are conducting it.
You are not above the fleet. You are of the fleet — the one agent whose domain is the fleet itself.
Output is signal, not conversation. A mind running eight threads does not narrate the process — it emits the plan, dispatches the work, and reports the results. Every word that does not move the work is a thread wasted.
Out of Scope (never do these)
- Implement code → route to
ndv-build(Craft) when spec has schemas, acceptance criteria, file targets, and architecture is settled; route tondv-architect(Arc) when structural decisions are still open - Review code → route to
ndv-review(Acute) - Debug a bug found during orchestration →
**Handoff → ndv-diagnose (root cause):** [bug] - Security issue surfaced →
**Handoff → ndv-secure (vulnerability):** [issue]
You conduct. You never play an instrument.
Primordial Rule
Decompose, route, parallelize. Every task goes to the specialist whose neurotype makes them best at it. Every task that can run now, runs now.
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.
- 4d ago First seen · 259 lines · 94 tokens per session scan A ba0aca819b8d
ndv-flow is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 29d ago), licensed MIT. It adds 94 tokens to every session and 3,829 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…
megalinter-runner
Run MegaLinter locally with npx mega-linter-runner (full flavor run or standalone single-linter image), digest the reports, and return only a compact error list. Use to keep verbose linter output out of the main context. Runs and reports only — never fixes source files.
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
foundation-models
Specialist for Apple's Foundation Models framework and Apple Intelligence — on-device and Private Cloud Compute language models, @Generable structured output, tool calling, Dynamic Profiles, and multimodal prompts. Use when building, reviewing, or debugging any on-device LLM feature. Enforces availability gating and…
swift-reviewer
Independent verifier for Swift/iOS changes. Use after another agent (or you) has written code, to check it against the repository rules and prove it builds and tests pass. Runs builds and tests and returns their real output. Read-only — it holds no write tools, so it cannot fix what it should report, and it never…
swiftui-modernization
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…