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 AlexShchuka/neuro-matrix --skill robust-by-constructiongit clone --depth 1 https://github.com/AlexShchuka/neuro-matrixWrote 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/alexshchuka/neuro-matrix/robust-by-construction)<a href="https://agentmods.dev/skills/alexshchuka/neuro-matrix/robust-by-construction"><img src="https://agentmods.dev/badge/skills/alexshchuka/neuro-matrix/robust-by-construction/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/alexshchuka/neuro-matrix/robust-by-construction"><img src="https://agentmods.dev/badge/skills/alexshchuka/neuro-matrix/robust-by-construction.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 | $0.00065 | $0.01692 |
| Opus 5 | $0.00032 | $0.00846 |
| Sonnet 5 | $0.00013 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
robust-by-construction 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Robust-by-construction: the invariant bar for systems built by this harness
BLUF: «works on my machine» is not the bar. The bar is: every failure surfaces, every wait has an escape, every operation is safe to repeat, and every rule that can be mechanized is mechanized. Prose is the last resort for what cannot be encoded.
(a) Fail-fast / error-as-data
No system error is swallowed. A false «success» on a failed operation is a security defect — the caller proceeds as if state was mutated when it was not.
Rules:
- Every error is propagated to ONE global handler (the observability sink). The handler decides: log + continue, degrade gracefully, or halt. Individual nodes do not make this call — they emit the error and let the global module handle it. This is «error-as-data»: a process does its work and emits its outcome (including failure) as structured data; it does not silently absorb failures.
- Degraded operation is the goal of failure handling, not suppression. A degraded state must be distinguishable from a healthy state by the system's own telemetry.
- Enforce mechanically:
forbidigo(Go) or equivalent linter rule blocking bare error discards (_ = err,if err != nil { return }without propagation).
Mirabilis example: the proxy lifecycle failure on first-launch was masked by a swallowed dial error — the TUI showed a connected state while the proxy was dead. The fix added error propagation to the observability sink and a health-check that distinguished «proxy not yet started» from «proxy running».
(b) No-hang / no-race
Every I/O, sync, and wait has a hard escape. «It will eventually complete» is not a correctness argument for a user-facing system.
Rules:
- Every blocking call carries a
contextdeadline (or timer) AND/OR a forced unblock path (close the fd, kill the process group, cancel the context). Both, where possible. - Long-lived resources (file locks, PTY handles, proxy processes) are owned for the session, not for a single call. Ownership means: created once, explicitly released on session teardown, never released by GC.
- Subscriptions (event listeners, channels, callbacks) are registered once per session, not re-created per event. Re-creation per event is a leak path.
- Enforce mechanically: the race detector (
-race) runs in CI on every branch; goroutine leak detectors (e.g.goleak) in test teardown.
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 · 96 lines · 65 tokens per session scan A b3bf5df680b0
robust-by-construction is a skill published in the GitHub repository AlexShchuka/neuro-matrix (3 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,692 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
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisQuarter
Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
harness
A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…