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 strikersam/autonomous-ai-agency --skill ai-engineering-insightsgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/ai-engineering-insights)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/ai-engineering-insights"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/ai-engineering-insights/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/strikersam/autonomous-ai-agency/ai-engineering-insights"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/ai-engineering-insights.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 | $0.00019 | $0.00447 |
| Opus 5 | $0.00010 | $0.00224 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
ai-engineering-insights 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
AI Engineering Insights Skill
Inspired by: DX Q1 AI-Assisted Engineering Impact Report
Purpose: Track engagement, performance, and tool quality for AI engineering tools — the metrics engineering leaders use to justify spend and pick winning vendors.
What's Unique About the DX Report
The DX report defines three metric pillars that local-llm-server now mirrors:
- Engagement — DAU/WAU, sessions per user, tool diversity. Adoption is a leading indicator of value.
- Performance — cycle-time delta (AI vs control), defect rate, throughput. Outcome metrics that show whether AI is actually moving the needle.
- Tool Quality — per-tool acceptance rate, latency, token efficiency. Helps choose between vendors objectively.
Module: agents/ai_insights.py
from agents.ai_insights import (
EngagementMetrics, PerformanceAnalytics, AIToolMetrics,
UsageEvent, ToolKind, build_report,
)
eng = EngagementMetrics()
eng.record(UsageEvent("alice", "claude_code", ToolKind.AGENT, datetime.now(), accepted=True))
eng.weekly_active_users() # → 1
Integration Points
- Telemetry pipeline — emit
UsageEventfrom agent loops, completion endpoints, chat handlers. - Dashboard — surface
build_report(...)output in admin GUI. - Vendor reviews — use
AIToolMetrics.tool_ranking()to compare tools objectively.
Key Design Choices
- Plain dataclasses, no external deps — drops cleanly into any service.
statistics.median— resistant to outliers (a single 100-hour PR doesn't skew cycle-time delta).- Session detection by gap — matches DX's definition of "engagement session".
References
- DX Report: https://getdx.com/report/ai-assisted-engineering-Q1-impact-report/
- Quick-Note Issue: #264
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 · 50 lines · 19 tokens per session scan A 60b02b19fa7f
ai-engineering-insights is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 447 once invoked, about $0.0001 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 skills, from other repositories
guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
chain-of-thought-prompts
Chain-of-thought and step-by-step reasoning prompts for complex problem solving.
chroma-integration
Chroma local vector database setup and operations for development and production.
few-shot-example-gen
Few-shot example generation and optimization for improved LLM performance.