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 aozyildirim/Agena --skill integration-rule-enginegit clone --depth 1 https://github.com/aozyildirim/AgenaWrote 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/aozyildirim/agena/integration-rule-engine)<a href="https://agentmods.dev/skills/aozyildirim/agena/integration-rule-engine"><img src="https://agentmods.dev/badge/skills/aozyildirim/agena/integration-rule-engine/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/aozyildirim/agena/integration-rule-engine"><img src="https://agentmods.dev/badge/skills/aozyildirim/agena/integration-rule-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00948 |
| Opus 5 | $0.00034 | $0.00474 |
| Sonnet 5 | $0.00013 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
integration-rule-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Rule Engine
When a Sentry / NewRelic / Jira / Azure DevOps event lands, you want to auto-tag it, route it to the right AI reviewer agent, and bump priority based on attributes — without rebuilding the routing logic in code per source. The Integration Rule Engine collapses all that into one rule table.
How to apply this pattern
-
Single rule table with
provider+match(JSON) +action(JSON) +priority(rule precedence) +is_active. Same shape across providers; the matcher just checks the appropriate attributes. -
Match clause — matches a single field with one operator. Common operators:
Operator Use equalsreporter is exactly [email protected]containstag list contains securityinreporter in ( [email protected],[email protected])regexerror class matches ^TypeError|^IntegrityError$prefixarea path starts with Project\Backend\ -
Action clause — what happens when the rule matches:
tag: add a tag string to the imported task (e.g.security_review)preferred_agent_role: which reviewer agent to route through (e.g.security_developer)priority: override priority (critical,high, etc.)target_repo: override the default repo mapping for this task
-
Evaluate at import time, not at agent run time. Stamp the action into the task's metadata so downstream agents and the UI see the same routing without re-evaluating.
-
First-match-wins with explicit priority. A rule with higher priority gets evaluated first; a single rule wins per import.
Example rules
# Security tickets reported by the security team go to the
# OWASP-aware reviewer with critical priority
- provider: jira
match: { field: reporter, op: in, values: [[email protected]] }
action:
tag: security_review
preferred_agent_role: security_developer
priority: critical
# Sentry errors in the payments project always route to a senior
# backend reviewer
- provider: sentry
match: { field: project, op: equals, value: payments }
action:
tag: payments
preferred_agent_role: senior_backend
priority: high
# Azure DevOps work items in a specific area path
- provider: azure_devops
match: { field: area_path, op: prefix, value: "Project\\Frontend" }
action:
tag: frontend
preferred_agent_role: a11y_reviewer
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 · 95 lines · 67 tokens per session scan A 5c7b4fc2a349
integration-rule-engine is a skill published in the GitHub repository aozyildirim/Agena (99 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 948 once invoked, about $0.0003 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 skills, from other repositories
error-logging
Log all errors with full context, detect patterns, and suggest approach mutations to avoid repeated failures.
ai-quality-complaint-8d-report
A business-diagnosis assistant for creating or reviewing an 8D report. An 8D report is a structured method for investigating a quality problem and documenting corrective action.
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
babysit-babysitter-issues
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
cog-meeting-processing
Process meeting recordings and transcripts into decisions, action items, and team dynamics.
cog-team-intelligence
Cross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefs.