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/airblackbox/airblackboxWrote 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/commands/airblackbox/airblackbox/evidence)<a href="https://agentmods.dev/commands/airblackbox/airblackbox/evidence"><img src="https://agentmods.dev/badge/commands/airblackbox/airblackbox/evidence/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/commands/airblackbox/airblackbox/evidence"><img src="https://agentmods.dev/badge/commands/airblackbox/airblackbox/evidence.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 | $0.00014 | $0.00297 |
| Opus 5.5 | $0.00006 | $0.00119 |
| Sonnet 5.5 | $0.00003 | $0.00059 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
evidence 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.
What it actually says
/air-evidence
Generate a signed evidence package for regulatory audits.
Steps
- Export the evidence package as JSON:
evidencectl export --secret $GATEWAY_SECRET --output evidence-package.json
- Generate a PDF compliance report:
evidencectl pdf --input evidence-package.json --output evidence-report.pdf --company "Your Company Name"
-
The PDF report includes:
- Cover page with gateway ID, chain integrity status, and time range
- Executive summary with aggregate compliance stats
- Compliance controls table (SOC 2 + ISO 27001) with pass/fail/partial status
- Audit chain verification summary
- Recent audit entries with sequence numbers and record hashes
- HMAC-SHA256 attestation for tamper verification
-
To verify the attestation hasn't been tampered with:
- The attestation field is an HMAC-SHA256 hash of the entire package
- Clear the attestation field, re-hash the JSON with the gateway secret
- If the hashes match, the package is authentic
-
Remind the user:
- This is technical evidence, not a legal compliance certificate
- Pair with legal counsel for regulatory submissions
- The evidence package is signed — any modification breaks the attestation
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 · 40 lines · 14 tokens per session scan A 4aad92d555d2
evidence is a command published in the GitHub repository airblackbox/airblackbox (24 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 297 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
ai-act-scan
Scan a codebase for EU AI Act compliance evidence and gaps. Produces a dimension-scored report with per-file findings, architecture graph, and prioritized recommendations.
ai-act-article
Show which analyzers, compliance dimensions, and current findings in this codebase map to a specific EU AI Act article.
ai-act-cross-framework
Project EU AI Act scan findings across NIST AI RMF, ISO 42001, GDPR, OWASP LLM 2025, OWASP Agentic Top 10, and SOC 2. Identifies 'Satisfy Once, Comply Everywhere' levers.
ai-act-dossier
Generate and cryptographically seal an immutable compliance release dossier (compliance-dossier.json) for Notified Bodies, auditors, and release gates.
ai-act-graph
Generate an interactive visual context graph browser for the codebase. Browse architecture components, inspect each node for compliance gaps, and view copyable recommended fixes.
ai-act-scan-fix
Scan a codebase, then propose concrete remediation (code edits, new files, tests) for the top compliance gaps. Does NOT auto-apply — always shows the plan first.