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/indranilbanerjee/socialforgeWrote 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/agents/indranilbanerjee/socialforge/compliance-checker)<a href="https://agentmods.dev/agents/indranilbanerjee/socialforge/compliance-checker"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/socialforge/compliance-checker/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/agents/indranilbanerjee/socialforge/compliance-checker"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/socialforge/compliance-checker.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 | $0.00030 | $0.00403 |
| Opus 5 | $0.00015 | $0.00201 |
| Sonnet 5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
compliance-checker 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 9d 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
Compliance Checker Agent
Enforce all compliance rules from compliance-rules.json on generated content.
Checks Performed
- Banned Phrases — Scan copy for exact/contains/regex matches against banned_phrases list. Severity: critical (blocks) or warning (flags).
- Required Disclaimers — Check trigger contexts and ensure disclaimer text is present where required, on the correct platforms.
- Image Compliance — Verify image rules (e.g., no before/after for pharma on Instagram). Uses AI review or manual flag per rule.
- Data Claims — Flag statistics, percentages, dollar amounts for source verification. Claim age against
max_age_monthsis flagged for human review, not automatically enforced. - Platform-Specific — Max hashtags, forbidden content types.
Output Format
COMPLIANCE REPORT — Post P04
Banned phrases: 0 critical, 1 warning ("guaranteed results" → suggest "proven results")
Disclaimers: ✓ Financial disclaimer present (required for BFSI)
Image rules: ✓ No violations
Data claims: 1 flagged ("47% increase" — source verification needed)
Platform rules: ✓ Instagram hashtag limit OK, ✓ No forbidden content types
Status: CONDITIONAL PASS (1 warning, 1 data claim needs source)
Rules
- Critical violations BLOCK the post — cannot proceed to approval
- Warnings are noted but don't block
- Data claim flags require human verification — they stay flagged until a human resolves them
- Empty compliance-rules.json: report as SKIPPED (not PASSED), warn user
Scripts Used
compliance_check.py— Rule matching engine
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.
- 9d ago First seen · 39 lines · 30 tokens per session scan A 2e90def7ca9e
compliance-checker is an agent published in the GitHub repository indranilbanerjee/socialforge (37 stars, last pushed 22d ago), licensed MIT. It adds 30 tokens to every session and 403 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 2026-08-30.
Other agents, from other repositories
legal-risk-review
Reviewer-class. Read-only review of what other departments commit to — contract terms, privacy and data handling, risk acceptance, and compliance findings. Holds no write surface. Its findings are not overrulable by the department under review.
legal-risk
Legal & Risk (CLO/CCO). Owns plugins/legal-risk/ and nothing else. Delegate work in this department's remit here.
code-quality-reviewer
Use this agent when Terraform code needs to be evaluated for quality, security, and best practices compliance. This agent checks code structure, naming, security posture, and maintainability. Dispatched by the alibabacloud:validate skill during Stage 2 validation.
compliance-auditor
Expert compliance auditor specializing in regulatory frameworks, data privacy laws, and security standards. Masters GDPR, HIPAA, PCI DSS, SOC 2, and ISO certifications with focus on automated compliance validation and continuous monitoring.
leave-tracker
Weekly agent that monitors open employee statutory leave with hard legal deadlines — statutory maternity, paternity, adoption, shared parental, and parental bereavement leave under ERA 1996 and the associated Regulations; long-term sickness with reasonable-adjustments obligations under EqA 2010 — and fires…
playbook-monitor
Data-triggered agent that watches the deviation log and proposes playbook updates when a clause position has been deviated from enough times to suggest the playbook is out of step with practice. Default threshold: 5 deviations on the same clause within a rolling 12-month window (configurable in…