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 | $0.00043 | $0.00636 |
| Sonnet 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 12d 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.
- 12d 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 2d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,272 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 skills, from other repositories
alexandria
Reach for this when a research question needs cited sources across academic papers, public domain books, legal records, government archives, security advisories, news, or developer documentation. Alexandria is an MCP server backed by 152 public digital libraries; use it whenever an answer should point at real…
halopsa
Every HaloPSA, HaloITSM and HaloCRM feature, plus a local SQLite store and cross-entity views the API can't return. Trigger phrases: triage my Halo queue, check SLA breaches in HaloPSA, who is overloaded in Halo, client card for Acme in Halo, Halo contract burn-down, what changed in Halo since this morning, find time…
cipp
First single-binary CLI for CIPP - offline SQLite store, fleet posture analytics, and cross-tenant fan-out no other CIPP tool has. Trigger phrases: check MFA across all my tenants, find unused M365 licenses, offboard users from a CSV in CIPP, which tenants drifted off baseline, list CIPP tenants, use cipp, run…
immybot
Every ImmyBot endpoint typed, plus a local SQLite mirror that answers the cross-tenant questions the web UI cannot. Trigger phrases: what failed in last night's maintenance window, which tenants are still on an old version of chrome, why didn't this computer get the deployment, what changed in the fleet since…
pagerduty
Every PagerDuty incident, on-call and service operation from the terminal, plus a local SQLite mirror that answers cross-entity questions - MTTA/MTTR, on-call coverage gaps, responder load - that neither the API nor the web UI can. Trigger phrases: who is on call for this service, show me the open pagerduty incidents…
pipedrive
Full Pipedrive CRUD plus a local SQLite pipeline copy: stale deals, forecasts, aging, dupes, rep leaderboards. Trigger phrases: which deals are going stale in pipedrive, what's my weighted pipeline forecast, who do I need to follow up with today, find duplicate contacts in pipedrive, show the sales rep leaderboard…