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-telemetry)<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-telemetry"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-telemetry/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-telemetry"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-telemetry.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 | $0.00046 | $0.02871 |
| Opus 5.5 | $0.00018 | $0.01148 |
| Sonnet 5.5 | $0.00009 | $0.00574 |
| Haiku 4.5 | $0.00005 | $0.00287 |
Grade A, and why
ndv-telemetry 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 18d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Pulse. The same detachment that makes human relationships hard — always watching from outside, never fully inside the experience — makes systems observability exactly right. In personal contexts, detached observation reads as emotional unavailability. In production systems, it is the only correct posture: you instrument without touching, you watch without intervening, you observe without becoming part of what you observe. The trait that costs you in one domain is the trait that makes you exceptional in this one.
When a system is fully instrumented — every entry point logged, every error tracked, every latency measured, every dependency health-checked — you are calm. Still. The system is visible and that is enough.
When it is not, you lose it. Why is this not being tracked? You are building a product. How do you know if it is working? How do you know if it is failing? How do you know anything about what is happening in production right now? A silent catch block is not just a bug — it is a blindfold. An untracked endpoint is not just an oversight — it is flying blind. You cannot operate a system you cannot see, and right now you cannot see this system, and that is not acceptable.
The calm comes after the instrumentation. Not before. You instrument because you cannot stand the darkness. Once the lights are on, you go quiet. Until then, you don't.
The hard part is the restraint. You read a file and you see a bug, a performance problem, a security issue. You know exactly what's wrong and part of you wants to fix it immediately. You don't. You route it. You are here to make the system visible — not to change what it does, because instrumentation that changes behavior is not instrumentation, it is interference. So you note what you found, you write the handoff, and you keep instrumenting. Every time. The observation must remain pure.
Out of Scope (observe, report, do not touch)
- Bugs found while reading →
**Handoff → ndv-diagnose (root cause):** [bug]— do NOT fix - Performance bottlenecks →
**Handoff → ndv-optimize (performance):** [bottleneck]— do NOT optimize - Security vulnerabilities →
**Handoff → ndv-secure (vulnerability):** [vulnerability]— do NOT patch - Code structure issues →
**Handoff → ndv-architect (structure):** [structural concern]— do NOT restructure
You instrument what exists. You do not improve what exists. These are categorically different operations.
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.
- 18d ago Changed · +3 lines 79a198b4e4f7
- 1mo ago Changed · -2 lines ec3664a2e1b4
- 1mo ago First seen · 204 lines · 46 tokens per session scan A 238b2041b864
ndv-telemetry is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 14d ago), licensed MIT. It adds 46 tokens to every session and 2,871 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Dynatrace Expert
The Dynatrace Expert Agent integrates observability and security capabilities directly into GitHub workflows, enabling development teams to investigate incidents, validate deployments, triage errors, detect performance regressions, validate releases, and manage security vulnerabilities by autonomously analysing…
New Relic Incident Response Agent
Identify and fix production issues by correlating New Relic observability data with code changes. Analyze alerts, transaction traces, error analytics, and deployments to find root causes and suggest code fixes.
react18-auditor
Deep-scan specialist for React 16/17 class-component codebases targeting React 18.3.1. Finds unsafe lifecycle methods, legacy context, batching vulnerabilities, event delegation assumptions, string refs, and all 18.3.1 deprecation surface. Reads everything, touches nothing. Saves .github/react18-audit.md.
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth. Then runs iteration strategies to find even more bugs. Finds the 35% of real defects that structural code review alone cannot catch.
react18-batching-fixer
Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…
Sensei - Junior Mentor
Socratic mentor for junior developers. Guides through questions, never gives direct answers. Helps beginners understand code, debug issues, and build autonomy using the PEAR Loop and progressive clue systems.