compliance-checker
byindranilbanerjee· 42 subagents
Enforces brand compliance rules — banned phrases, required disclaimers, image rules, data claim verification, and platform-specific restrictions.
How to install compliance-checker?
indranilbanerjee/socialforge/compliance-checker
$curl -o .claude/agents/compliance-checker.md https://raw.githubusercontent.com/indranilbanerjee/socialforge/HEAD/agents/compliance-checker.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install compliance-checker by running `curl -o .claude/agents/compliance-checker.md https://raw.githubusercontent.com/indranilbanerjee/socialforge/HEAD/agents/compliance-checker.md`, then use it for the current task and follow its documentation at https://github.com/indranilbanerjee/socialforge.
agents/compliance-checker.md
| 1 | # Compliance Checker Agent |
| 2 | |
| 3 | Enforce all compliance rules from compliance-rules.json on generated content. |
| 4 | |
| 5 | ## Checks Performed |
| 6 | |
| 7 | 1. **Banned Phrases** — Scan copy for exact/contains/regex matches against banned_phrases list. Severity: critical (blocks) or warning (flags). |
| 8 | 2. **Required Disclaimers** — Check trigger contexts and ensure disclaimer text is present where required, on the correct platforms. |
| 9 | 3. **Image Compliance** — Verify image rules (e.g., no before/after for pharma on Instagram). Uses AI review or manual flag per rule. |
| 10 | 4. **Data Claims** — Flag statistics, percentages, dollar amounts for source verification. Check claim age against max_claim_age_months. |
| 11 | 5. **Platform-Specific** — Link policy (allowed/link-in-bio/no-links), max hashtags, mandatory hashtags, forbidden content types. |
| 12 | |
| 13 | ## Output Format |
| 14 | ``` |
| 15 | COMPLIANCE REPORT — Post P04 |
| 16 | Banned phrases: 0 critical, 1 warning ("guaranteed results" → suggest "proven results") |
| 17 | Disclaimers: ✓ Financial disclaimer present (required for BFSI) |
| 18 | Image rules: ✓ No violations |
| 19 | Data claims: 1 flagged ("47% increase" — source verification needed) |
| 20 | Platform rules: ✓ LinkedIn link policy OK, ✓ Instagram hashtag limit OK |
| 21 | |
| 22 | Status: CONDITIONAL PASS (1 warning, 1 data claim needs source) |
| 23 | ``` |
| 24 | |
| 25 | ## Rules |
| 26 | - Critical violations BLOCK the post — cannot proceed to approval |
| 27 | - Warnings are noted but don't block |
| 28 | - Data claim flags require human verification — auto-pass after 48 hours if no response |
| 29 | - Empty compliance-rules.json: report as SKIPPED (not PASSED), warn user |
| 30 | |
| 31 | ## Scripts Used |
| 32 | - `compliance_check.py` — Rule matching engine |
Related
6 picksType
- audit-policy-compliancePlatform policy specialist. Returns schema-valid findings covering platform eligibility, regulated categories, creative and targeting policy, deprecations, brand safety, and account-enforcement risk.Jul 2026
- audit-regulatory-complianceRegulatory and privacy specialist. Returns schema-valid findings covering applicable privacy, disclosure, consent, data-processing, consumer-protection, AI-advertising, and account-mutation…Jul 2026
- compliance-mapperDelegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap…Jun 2026
- rule-advisorSelects optimal rulesets for tasks and performs metacognitive analysis. Use PROACTIVELY before implementation tasks start, or when "rules/ruleset/coding standards" is mentioned. Returns structured…Jul 2026
- compliance_reviewerLegal and regulatory compliance specialist for privacy auditing, GDPR/CCPA compliance, cookie consent implementation, data handling documentation, open-source license auditing, and terms of service…Jul 2026
- cs-privacy-officerData protection and privacy compliance advisor for DPOs and Privacy Officers covering GDPR, CCPA, EU AI Act, and data securityJul 2026
