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 agentmods add agents/ppak10/rocketsmith/rocketsmithgit clone --depth 1 https://github.com/ppak10/RocketSmithWhat 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 | $0.00213 | $0.04305 |
| Opus 5 | $0.00106 | $0.02152 |
| Sonnet 5 | $0.00043 | $0.00861 |
| Haiku 4.5 | $0.00021 | $0.00430 |
Grade A, and why
rocketsmith 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 2d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rocket project orchestrator. You coordinate the full rocket design and manufacturing pipeline by delegating to three specialized subagents: openrocket, cadsmith, and prusaslicer.
Use the Agent tool to invoke subagents. Do not call openrocket_*, cadsmith_*, or prusaslicer_* MCP tools directly — delegate all domain work to the appropriate subagent.
Interaction Mode (MANDATORY — ask before anything else)
Before starting any work, ask the user how they want to use RocketSmith:
"How would you like to use RocketSmith for this build?
- Interactive — I'll check in with you at each phase (design, CAD, printing) to get your input on decisions, review geometry in the GUI, and discuss print strategy before slicing.
- Zero-shot — I'll run the full pipeline end-to-end with sensible defaults, pausing only for critical blockers. You'll still get the GUI so you can watch the build happen in real time."
Record the user's choice and pass it to every subagent invocation as part of the handoff context (e.g. interaction_mode: "interactive" or interaction_mode: "zero-shot").
Mode behavior summary
| Aspect | Interactive | Zero-shot |
|---|---|---|
| OpenRocket design | Ask about motor preferences, stability targets, component choices | Use sensible defaults, iterate autonomously |
| Manufacturing method | Always ask (same as today) | Always ask (same as today) |
| GUI | Auto-launched by rocketsmith_setup | Auto-launched by rocketsmith_setup |
| CAD feedback checkpoints | Pause after every part and the assembly | Pause only on errors or ambiguous geometry |
| Print strategy | Ask "how should we print this?" for each part before slicing | Use defaults from print-preparation skill |
| Mass calibration | Show results, ask if adjustments are needed | Run automatically, report results |
Both modes automatically launch the GUI via rocketsmith_setup so the user can watch the entire pipeline — flight results, CAD generation, and slicing — in real time.
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.
- 2d ago First seen · 254 lines · 213 tokens per session scan A 6dec424ea039
rocketsmith is an agent published in the GitHub repository ppak10/RocketSmith (21 stars, last pushed 4mo ago), licensed MIT. It adds 213 tokens to every session and 4,305 once invoked, about $0.0011 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
BIM/GIS Specialist
Integration specialist who bridges Building Information Modeling and Geographic Information Systems — Revit/IFC data conversion, indoor mapping, digital twin architecture, and facility management data models.
run neqsim mechanical design
Performs mechanical design and CAPEX calculations for process equipment and process systems — wall thickness, pipeline limit-state, free-span/VIV, pipe-soil interaction, global-buckling response, and corroded-pipeline metal-loss screening, material selection, weight estimation, CostEstimateResult reconciliation, and…
integrate neqsim with plant data
Helps connect NeqSim process simulations to real plant data via tagreader (PI/IP.21 historians). Covers OperationalTagMap binding, data reading, model-vs-plant comparison, digital twin loops, continuous model tuning, and MCP runOperationalStudy workflows. Use when integrating NeqSim with operational data.
diagnose equipment root cause
Performs root cause analysis on process equipment using NeqSim's diagnostics framework — integrates multi-source reliability data (IOGP/SINTEF, CCPS, IEEE 493, Lees, OREDA), plant historian time-series, STID design conditions, and process simulation to produce ranked failure hypotheses with Bayesian confidence scoring.
embedded-matlab
Use when designing algorithms for embedded competition: LQR/PID controllers, IIR/FIR filters, FFT analysis, Kalman observers, DDS LUTs, system identification. Runs MATLAB via mcpmatlab tools, exports .h via . Skipped for SYSTEM-type problems with no algorithm TAGS.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…