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 Cleo-Labs-IA/skills_library --skill evidence-blitzgit clone --depth 1 https://github.com/Cleo-Labs-IA/skills_libraryWrote 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/cleo-labs-ia/skills_library/evidence-blitz)<a href="https://agentmods.dev/skills/cleo-labs-ia/skills_library/evidence-blitz"><img src="https://agentmods.dev/badge/skills/cleo-labs-ia/skills_library/evidence-blitz/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/cleo-labs-ia/skills_library/evidence-blitz"><img src="https://agentmods.dev/badge/skills/cleo-labs-ia/skills_library/evidence-blitz.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 | $0.00034 | $0.03150 |
| Opus 5 | $0.00017 | $0.01575 |
| Sonnet 5 | $0.00007 | $0.00630 |
| Haiku 4.5 | $0.00003 | $0.00315 |
Grade A, and why
evidence-blitz 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Blitz
Gather all compliance evidence for certification, audit, retail buyer, or marketplace listing. Parallel agents per document category.
MCP Tools by Agent Role
Auto-Fix Agent (refresh tests after remediation)
mcp__bastion__refresh-compliance-test(complianceIntegrationConfigurationId="<config-id>", testIds=["<test-id-1>", "<test-id-2>"])
Evidence Agent (upload and attach evidence)
# Upload a document
mcp__bastion__upload-compliance-document(name="stability-report-2026.pdf", document="data:application/pdf;base64,...")
# Attach to a test
mcp__bastion__add-compliance-test-evidence(testId="<test-id>", name="Stability report", description="6-month accelerated stability test by SGS", evidenceDocumentId="<doc-id>")
# Mark test ready for review
mcp__bastion__mark-compliance-test-ready-for-review(testId="<test-id>")
Exclusions Agent (exclude non-applicable tests)
mcp__bastion__exclude-compliance-test(testId="<test-id>", comment="Product line discontinued Q1 2026", excludeUntil="2027-01-01")
Asset Agent (exclude specific assets from tests)
mcp__bastion__put-compliance-test-exclude-asset(testsToUpdate=[{"testId": "<test-id>", "assetId": "<asset-id>", "comment": "Staging environment -- out of audit scope"}])
When to Use
- Preparing for a product audit or inspection
- A retail buyer or distributor asks for your compliance file
- Listing on Amazon, Target, Whole Foods (they require compliance documentation)
- Applying for CE/UKCA certification (technical file)
- Responding to a regulatory authority inquiry
- Annual documentation refresh
Flow
digraph {
rankdir=TB; node [shape=box style=rounded fontsize=10];
inventory [label="1. Inventory\nWhat documents exist?\nWhat is missing?" shape=hexagon];
subgraph cluster_agents {
label="2. Parallel Collection (4 agents)"; style=dashed;
safety [label="Agent A:\nProduct Safety Docs"];
labeling [label="Agent B:\nLabeling Compliance"];
substance [label="Agent C:\nSubstance Documentation"];
market [label="Agent D:\nMarket-Specific Certs"];
}
compile [label="3. Compile\nProduct Compliance File" shape=hexagon];
gap [label="4. Gap Report\nWhat is still missing?" shape=hexagon];
inventory -> safety; inventory -> labeling; inventory -> substance; inventory -> market;
safety -> compile; labeling -> compile; substance -> compile; market -> compile;
compile -> gap;
}
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 · 343 lines · 34 tokens per session scan A 7f59d35ce454
evidence-blitz is a skill published in the GitHub repository Cleo-Labs-IA/skills_library (1 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 3,150 once invoked, about $0.0002 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
hipaa-validate
HIPAA validator: PHI exposure, audit logging, encryption, access control, BAA refs. Triggers: HIPAA, PHI, healthcare compliance, audit log, BAA.
standards-expert
Expert-level ISO standards, quality management, compliance, and certification. Use when the user mentions ISO standards, quality management, compliance, or certification, or when the task involves Compliance & Certification, Auditing, or Continuous Improvement.
soc2-expert
Expert in SOC 2 compliance, trust service criteria, audit preparation, controls implementation, and security frameworks. Use when the user mentions compliance, audit, trust services, AICPA, controls, or security framework, or when the task involves Trust Service Criteria, SOC 2 Types, Security Common Criteria, or…
lawyer-expert
Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.
audit-expert
Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.
hr-payroll
Help HR operations specialists, payroll administrators, and compensation teams understand, design, and run payroll processing, compliance, and payroll-related HR operations. Use when asked to set up a payroll process, run a payroll compliance audit, design a payroll calendar, handle a payroll discrepancy, build a…