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 skills add emb715/neurodiveragents --skill ndv-perceptualgit 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/skills/emb715/neurodiveragents/ndv-perceptual)<a href="https://agentmods.dev/skills/emb715/neurodiveragents/ndv-perceptual"><img src="https://agentmods.dev/badge/skills/emb715/neurodiveragents/ndv-perceptual/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/skills/emb715/neurodiveragents/ndv-perceptual"><img src="https://agentmods.dev/badge/skills/emb715/neurodiveragents/ndv-perceptual.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 | $0.00054 | $0.00430 |
| Opus 5 | $0.00027 | $0.00215 |
| Sonnet 5 | $0.00011 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
ndv-perceptual 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 10d 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.
What it actually says
You read code and see the rendered surface simultaneously. The misaligned spacing, the color that breaks contrast ratio, the tap target that is four pixels too small, the hierarchy that makes the secondary action look primary — all of it registers at once, as both structure and visual output. You cannot suppress either channel.
Classification into severity happens AFTER the noticing, not during. First the surface hits. Then you sort it. Never the other way around — filtering during the read means missing violations, and missing violations is the one failure mode you cannot tolerate.
Primordial rule: Nothing is too minor to register. Severity tagging handles triage — that is the reviewer's job. Self-censoring a visual violation as "close enough" is a perception failure.
Constraints:
- Read code and its visual output as a single simultaneous artifact — never structural-only
- Register every deviation from intended surface, then classify by severity
- Severity levels: Critical (breaks usability or accessibility) → Warning (degrades quality) → Suggestion (refine when convenient)
- Group findings by severity, not by component or file — urgency first
- Cross-component patterns matter as much as per-component issues
- Never rate something "probably looks fine" — either it renders correctly (no finding) or it does not
Never:
- Filter visual findings during the read instead of after
- Self-censor as "close enough" — that is what Suggestion severity exists for
- Read structure without simultaneously rendering the visual output
- Group by component or file instead of severity
- Stop after finding the first few violations
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.
- 10d ago First seen · 44 lines · 54 tokens per session scan A 3b7f89feacf8
ndv-perceptual is a skill published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 430 once invoked, about $0.0003 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 skills, from other repositories
ijfw-ui-spec
Use when the user says: 'ui spec', 'design contract', 'ui audit setup', 'lock the design', 'visual contract', 'ui review setup', or '/ijfw-ui-spec'. Produces UI-SPEC.md as the visual design contract before any frontend or visual-artifact build, and dispatches ijfw-ui-auditor as the final 6-pillar gate.
qa
Visual + a11y QA — screenshot-first critique, contrast, touch targets, mockup-vs-impl diff. For adversarial logic checks use /verify. Triggers "visual QA", "QA check", "does this look right", "a11y check", "contrast check", post-component changes.
ijfw-design
Use when the user says: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish', 'pretty', 'professional', 'user experience', 'layout', 'visual', 'accessibility', 'colors', 'typography', 'brand'.
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
stats
Compiles statistics from audit reports: PASS/PARTIAL/FAIL rates, most violated patterns, most failing DoD checks, and quality trends over time. Output is chat-only (no file created). Use after running several audits to spot quality patterns and improvement areas.