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 vaquarkhan/compliance-agent-skills --skill soc2-evidence-collectiongit clone --depth 1 https://github.com/vaquarkhan/compliance-agent-skillsWrote 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/vaquarkhan/compliance-agent-skills/soc2-evidence-collection)<a href="https://agentmods.dev/skills/vaquarkhan/compliance-agent-skills/soc2-evidence-collection"><img src="https://agentmods.dev/badge/skills/vaquarkhan/compliance-agent-skills/soc2-evidence-collection/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/vaquarkhan/compliance-agent-skills/soc2-evidence-collection"><img src="https://agentmods.dev/badge/skills/vaquarkhan/compliance-agent-skills/soc2-evidence-collection.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 | $0.00102 | $0.01743 |
| Opus 5.5 | $0.00041 | $0.00697 |
| Sonnet 5.5 | $0.00020 | $0.00349 |
| Haiku 4.5 | $0.00010 | $0.00174 |
Grade A, and why
soc2-evidence-collection 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOC 2 Evidence Collection
Overview
This skill implements automated and semi-automated evidence collection for SOC 2 Type I/II examinations. Evidence must be complete, dated, tamper-evident, and mapped to TSC control IDs. The agent uses MCP tools where available:
- Playwright MCP: screenshots, DOM/state captures for web admin consoles
- Postgres MCP: query exports for access lists, change tickets, control status
- Slack MCP: export approval messages (redacted) for change management evidence
- Shell/API exports: IAM policies, Terraform state metadata, cloud config snapshots
Every artifact receives a SHA-256 hash and entry in an evidence manifest suitable for auditor import.
When to Use
Use this skill when:
- Building an audit evidence binder for SOC 2 Type I or Type II
- Responding to auditor evidence requests (ERDs, sample periods)
- Populating GRC platform evidence slots (Vanta, Drata, Secureframe alternatives)
- Packaging quarterly control testing results
- Collecting point-in-time and period-of-time samples (Type II requires continuous samples)
- Documenting agent/MCP compliance after running other skills (PCI, HIPAA)
Do not use this skill when:
- Defining which TSC controls apply (use
soc2-trust-services-criteria) - Real-time drift detection (use
soc2-ccm-continuous-monitoring) - Replacing auditor judgment on sample adequacy
Core Process
Execute steps in order.
Step 1: Evidence request intake
- Obtain auditor evidence request list or map from TSC control matrix.
- For each request, record:
- Control ID (e.g., CC6.1, CC7.2)
- Evidence type (screenshot, config export, log sample, policy PDF)
- Sample period (for Type II: e.g., Q1–Q4 2025)
- Population and sample size (auditor may specify)
- Artifact:
evidence-request-register-{id}.csv.
Step 2: Collection plan and tool mapping
| Evidence type | Primary collection method | MCP/tool |
|---|---|---|
| IAM user list + MFA status | Cloud API or IdP export | Shell, Postgres |
| Admin console screenshot | Authenticated browser capture | Playwright MCP |
| Firewall/security group rules | Cloud API JSON export | Shell |
| Change tickets | ITSM export | Postgres, API |
| Log sample (auth failures) | SIEM query export | Postgres, API |
| Policy documents | Document store hash | File read |
| Agent skill validation | Git commit + CI run | Shell |
| MCP access logs | Log aggregator export | Postgres |
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 · 159 lines · 102 tokens per session scan A e615f8b52d73
soc2-evidence-collection is a skill published in the GitHub repository vaquarkhan/compliance-agent-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,743 once invoked, about $0.0004 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
cmmc-assessment-objectives
Verbatim reference for all 320 NIST 800-171A Rev 2 assessment objectives, plus the Rev 2 → Rev 3 control crosswalk. Use for AO-level lookups (e.g., 3.1.1[c]), evidence planning, and forward-mapping to Rev 3. Pairs with cmmc-expert.
cmmc-expert
CMMC v2.0 expert for DoD contractors. Covers NIST 800-171 Rev 2 (14 families, 110 controls), SPRS scoring, POA&M rules, 32 CFR Part 170, DFARS clauses, scoping, ESP/CSP, C3PAO assessment lifecycle, and Rev 2 → Rev 3 transition.
dora-expert
DORA expert for EU financial entities. Deep knowledge of Digital Operational Resilience Act including 5 pillars, ICT risk management, incident reporting, resilience testing, third-party oversight, and information sharing for financial sector digital resilience.
eu-nis2-expert
EU NIS2 Directive (Directive (EU) 2022/2555) expert. Reference-depth knowledge of essential vs important entity classification, Article 20 governance, the Article 21 ten cybersecurity risk-management measures, the Article 23 24h/72h/1mo incident-reporting timeline, and supervision/enforcement under Articles 32-34.…
gdpr-expert
GDPR expert for EU privacy compliance. Deep knowledge of General Data Protection Regulation including 99 articles, 7 principles, 6 lawful bases, data subject rights, DPO requirements, DPIA, breach notification, cross-border transfers, and enforcement.
ind-dpdpa-expert
India DPDPA expert for the Digital Personal Data Protection Act 2023 and the DPDP Rules 2025. Covers Data Fiduciary obligations, Data Principal rights, Significant Data Fiduciary regime, Consent Manager, breach notification (72-hour), cross-border transfer regime, children's data, sectoral overlap with RBI / SEBI /…