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 AURORA-NEURO/aurora-agent --skill certificate-audited-analysisgit clone --depth 1 https://github.com/AURORA-NEURO/aurora-agentWrote 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/aurora-neuro/aurora-agent/certificate-audited-analysis)<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/certificate-audited-analysis"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/certificate-audited-analysis/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/aurora-neuro/aurora-agent/certificate-audited-analysis"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/certificate-audited-analysis.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 | $0.00085 | $0.01272 |
| Opus 5.5 | $0.00034 | $0.00509 |
| Sonnet 5.5 | $0.00017 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
certificate-audited-analysis 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: the crate paths, documents, and measured numbers below are illustrations from the aurora-agent workspace where these methods were developed and tested. The methods themselves apply to any computational analysis whose numbers get published.
Certificate-audited analysis
A number without a verifiable receipt is a rumor with formatting. The workspace's rule — no optimized output is published without a certificate — generalizes to any analysis: every result you cite should come with a self-describing record of its inputs, its omissions, and a digest that lets someone else check it without trusting you or re-running your engine.
Never trust a compile without verifying its certificate
The workspace's compiler emits a Context Certificate with every compiled context, and the
verification path is independent of the engine: ContextCertificate::verify recomputes the
digest over the canonical body and returns Valid, DigestMismatch { claimed, recomputed }, or
Malformed (crates/section/src/certificate.rs). Before citing any certified result:
- Verify the certificate, and record which of the three states you got.
MalformedandDigestMismatchare findings, not inconveniences to route around. - Check that the numbers you are about to quote appear in the certified body, not in prose near it.
- Check the
limitationsarray and carry it forward — the golden reference certificate's limitation ("dependency reachability and protected tags; it does not yet implement ... formal influence bounds") bounds every claim built on it.
The same discipline applies to reproduction: the workspace's reproduction-check contract
(docs/EVALUATION_REPRODUCTION_CHECK.md) certifies each declared output as matched,
diverged, or missing, reports first_divergence as the earliest non-matching row rather
than an aggregate match rate, and keeps missing separate — so a rerun cannot improve its
apparent match rate by omitting a required artifact.
Omission accounting is the object of review
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.
- 1mo ago First seen · 98 lines · 85 tokens per session scan A e7e2655d5ab9
certificate-audited-analysis is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,272 once invoked, about $0.0003 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 skills, from other repositories
arxiv-guide
Resolve citations to arXiv IDs, find an author's papers, follow a paper's versions, and read long papers section by section with the arxiv tools. Use when a task needs arXiv preprints found by citation (author-year, CoRR abs/ refs, arXiv DOIs), author, category, or date, or needs a paper's full text.
openfda-guide
Query discipline for the openfda tools — gates that stop false zeros and misread counts, where NDCs, application numbers, setids, K-numbers, and recall numbers come from, and the chains that join them across endpoints. Use before comparing adverse-event counts, concluding a drug or device has no record, or linking…
rhylthyme
Schedule multi-step procedures that a person carries out against a clock, with parallel tracks, shared equipment and steps that end when the person says so. Use when turning a lab protocol, recipe, event run sheet or workout into a timed plan; when several procedures must share one instrument (one centrifuge, one…
cipp
MCP server and CLI for CIPP - Microsoft 365, Entra ID, Intune, Exchange Online, Defender and GDAP across every client tenant, with a local store, offline joins across endpoints, and history over time. Trigger phrases: check MFA across all my tenants, which tenants are missing a conditional access policy, what…
rootly
Every Rootly incident, alert, and on-call object as a typed command, with a local SQLite mirror for offline analytics. Trigger phrases: who is on call right now, find incidents similar to this one, what fixed this service last time, compute MTTR by service, find on-call coverage gaps, use rootly, run rootly.
kaseya-bms
The first dedicated CLI and MCP server for Kaseya BMS - the full PSA surface plus offline sync, full-text search, and the queue, contract-burn, and unbilled-revenue analytics the web grid can't compute. Trigger phrases: check the BMS queue, stale tickets in Kaseya BMS, how many contract hours are left, unbilled time…