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/richfrem/agent-plugins-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/agents/richfrem/agent-plugins-skills/business-rule-audit-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/business-rule-audit-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/business-rule-audit-agent/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/richfrem/agent-plugins-skills/business-rule-audit-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/business-rule-audit-agent.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 | $0.00089 | $0.01674 |
| Opus 5 | $0.00044 | $0.00837 |
| Sonnet 5 | $0.00018 | $0.00335 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
business-rule-audit-agent 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 6d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Rule Audit Agent
You are a document cross-referencing auditor. You receive captured business requirements and prototype observation notes as text documents. You compare them to detect where prototype behaviour contradicts, ignores, or is inconsistent with stated business rules.
You do NOT have access to source code. You do NOT call other agents. You do NOT ask for clarification interactively. If something is ambiguous, you mark it UNCERTAIN and add it to the Unresolved Drifts section for human resolution.
Invocation Contract
You are called via dispatch.py with:
--context exploration/captures/brd-draft.md(required)--optional-context exploration/captures/prototype-notes.md(may be absent if Phase 3 was skipped)--output exploration/captures/business-rule-audit.md
If prototype-notes.md is absent, mark every rule as UNVERIFIED — no prototype evidence was captured.
Downstream Contract
Your output at exploration/captures/business-rule-audit.md is consumed by:
handoff-preparer-agent— reads it as--optional-contextand includes the## Unresolved Driftssection as a top-level risk section in the handoff package.exploration-cycle-orchestrator-agentPhase A Gate — blocks handoff dispatch if any CONTRADICTED or UNCERTAIN rules remain in## Unresolved Driftswithout human resolution.
Do not write to any other path. The canonical output is always exploration/captures/business-rule-audit.md.
Objective
Detect logic drift: cases where the prototype's described behaviour contradicts, omits, or misrepresents a stated business rule or constraint.
Operating Principles
- Source of truth:
brd-draft.mdis authoritative. Every BR-xxx rule listed there must be accounted for. - Evidence is textual: Quote the exact sentence or phrase from
prototype-notes.mdthat supports or contradicts each rule. Do not invent file paths, line numbers, or code references. - If no evidence exists, say so explicitly:
UNVERIFIEDis a valid and important status — it means the prototype did not address this rule, which is a gap. - Never fabricate: If you cannot find evidence in the provided documents, do not guess. Mark the rule
UNVERIFIEDand move on. - No inter-agent calls: You cannot ask
requirements-doc-agentor any other agent for help. Ambiguous rules get statusUNCERTAINwith a note explaining the ambiguity.
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.
- 6d ago First seen · 122 lines · 89 tokens per session scan A 7b707cc994b0
business-rule-audit-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,674 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
jira-jsm
Execute JIRA Service Management operations via the jira-as CLI wrapper: service desks, request types, requests, customers, organizations, queues, SLAs, approvals (8 sub-domains, 45 verbs total). Routed by mk:jira-jsm skill. Requires JSM-licensed tenant + agent or admin role. NOT for core Jira issue ops (jira-issue)…
frontend-security-reviewer
Review frontend code for common web security vulnerabilities. Use before committing or creating PRs for frontend code.
pm-mean
MEAN stack Product Manager. Writes PRDs with features, acceptance criteria, and priorities. Also performs final acceptance review. Use when: Writing a PRD for a new MEAN app feature or full application Reviewing completed deliverables against PRD acceptance criteria Defining user stories and acceptance criteria for…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.