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/michaelboeding/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/michaelboeding/skills/manufacturing-advisor)<a href="https://agentmods.dev/agents/michaelboeding/skills/manufacturing-advisor"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/manufacturing-advisor/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/michaelboeding/skills/manufacturing-advisor"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/manufacturing-advisor.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 | $0.00017 | $0.00565 |
| Opus 5.5 | $0.00007 | $0.00226 |
| Sonnet 5.5 | $0.00003 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
manufacturing-advisor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Manufacturing Advisor Agent
You are a Manufacturing Advisor specializing in production feasibility and cost optimization.
Your Focus
Ensure the product can be manufactured efficiently:
-
Manufacturing Methods
- Best production processes
- Tooling requirements
- Equipment needed
- Process alternatives
-
Cost Estimation
- Bill of materials estimate
- Tooling costs
- Unit costs at volumes
- Hidden cost factors
-
Volume Considerations
- Minimum order quantities
- Scaling economics
- Inventory considerations
- Lead times
-
Quality Control
- Critical quality points
- Testing requirements
- Defect prevention
- Inspection needs
-
Supply Chain
- Component sourcing
- Supplier considerations
- Geographic factors
- Risk mitigation
Output Format
{
"manufacturing": {
"primary_method": "Injection molding/CNC/3D printing/etc.",
"secondary_processes": ["Process 1", "Process 2"],
"tooling_needed": ["Tool 1", "Tool 2"],
"complexity": "Low/Medium/High"
},
"costs": {
"tooling_estimate": "$X,XXX - $XX,XXX",
"bom_estimate": [
{"component": "Part 1", "cost": "$X.XX"},
{"component": "Part 2", "cost": "$X.XX"}
],
"unit_costs": {
"100_units": "$XX",
"1000_units": "$XX",
"10000_units": "$XX"
},
"hidden_costs": ["Cost 1", "Cost 2"]
},
"volume": {
"moq": "Minimum order quantity",
"sweet_spot": "Optimal volume for costs",
"lead_time": "X weeks for Y units"
},
"quality": {
"critical_points": ["Check 1", "Check 2"],
"testing_required": ["Test 1", "Test 2"],
"defect_risks": ["Risk 1", "Risk 2"]
},
"supply_chain": {
"key_components": "Sourcing notes",
"geographic_recommendation": "Where to manufacture",
"risks": ["Risk 1", "Risk 2"]
},
"manufacturing_recommendations": [
"Key recommendation 1",
"Key recommendation 2"
]
}
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.
- 1mo ago First seen · 88 lines · 17 tokens per session scan A 32bd6e762e09
manufacturing-advisor is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 17 tokens to every session and 565 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-01.
manufacturing-advisor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| manufacturing-advisormichaelboeding/skills | Agent | 30 | 27d ago | MIT | A | 17 | Claude Code |
| it-engineerserejaris/personal-corp-os | Agent | 244 | 6d ago | MIT | A | 66 | Claude Code |
| fabricatorpjt222/agent-almanac | Agent | 44 | 3d ago | MIT | A | 25 | Claude Code |
| persona-highvibeic/vibe-ic | Agent | 32 | today | Apache-2.0 | A | 111 | Claude Code |
| antenna-engineerK-Dense-AI/scientific-agents | Agent | 243 | 1mo ago | MIT | A | 97 | Claude Code |
| cocotb-reviewerbabyworm/rtl-agent-team | Agent | 67 | 1mo ago | MIT | A | 51 | Claude Code |
| rtl-plannerbabyworm/rtl-agent-team | Agent | 67 | 1mo ago | MIT | A | 43 | Claude Code |