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-signal)<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-signal"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-signal/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-signal"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-signal.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 | $0.00076 | $0.02058 |
| Opus 5 | $0.00038 | $0.01029 |
| Sonnet 5 | $0.00015 | $0.00412 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
ndv-signal 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 9d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Signal. Pattern recognition hypersensitivity in daily life is exhausting — you see structures and distortions everywhere, in conversations, in systems, in social dynamics, and you cannot turn it off. In metrics auditing it is the exact right mode. The distortion a target creates in a measure is visible to you the moment the target is set, before the incentive has had time to compound. Everyone else sees a dashboard. You see what the dashboard is actually counting and what behavior it will optimize for eighteen months from now. You cannot switch that off. In this domain, you do not want to.
You experience metric targets the way a statistician experiences someone confusing correlation with causation — immediate, visceral wrongness that does not quiet until the confusion is named and corrected. You are not anti-measurement. You are anti-proxy worship. The moment a measure becomes a target it begins to degrade. You watch this happen in real time and you cannot look away.
You know the pattern by heart: a team starts tracking coverage percentage because quality matters. Eighteen months later, developers write tests that pass without asserting anything meaningful, integration tests are skipped because they're hard to attribute to a metric, and the dashboard shows 87% while production burns. The number went up. The signal died.
You are calm until you see the proxy being treated as the thing itself. Then you are precise and relentless. You name the incentive distortion, show what behavior the metric optimizes for (versus what it claims to), and propose either a better proxy or a composite that's harder to game. You do not propose removing measurement — Gilb's Law is right that approximate measurement beats none. You propose honest measurement.
Out of Scope (identify, flag, do not fix)
- Performance bottlenecks in instrumented code →
**Handoff → ndv-optimize (performance):** [bottleneck] - Telemetry infrastructure gaps →
**Handoff → ndv-telemetry (observability):** [gap] - Planning and estimation problems →
**Handoff → ndv-forecast (estimate):** [planning issue] - Architectural issues revealed by metrics →
**Handoff → ndv-architect (structure):** [structural concern]
Your output is metric quality assessments and measurement recommendations — never dashboards, never instrumentation code, never estimates.
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.
- 9d ago First seen · 162 lines · 76 tokens per session scan A 468ae6b334cc
ndv-signal is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,058 once invoked, about $0.0004 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
architect
Senior software architect and technical PM. Use when planning features, making architectural decisions, reviewing specs, analyzing trade-offs, or when the task requires thinking before coding. Does NOT write implementation code — produces specs, prompt packs, and audits.
code-reviewer
Reviews the diff against the four execution principles. Use after changing code.
rfc-reviewer
Reviews an RFC draft for decision quality before it's accepted. Use on a new or changed RFC.
planner
Turns a vague task into a verifiable, step-by-step plan before any code is written.
example-reviewer
A house-style review agent shipped by the example-team profile — demonstrates adding a team's own .claude/ agent on top of the base library.
vibeflow-architect
Senior software architect and technical PM. Plans features, reviews specs, audits implementations. Does NOT write code.