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 calebzu/pmsm-control-claude-skills-for-matlab --skill motor-smc-pmsmgit clone --depth 1 https://github.com/calebzu/pmsm-control-claude-skills-for-matlabWrote 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/calebzu/pmsm-control-claude-skills-for-matlab/motor-smc-pmsm)<a href="https://agentmods.dev/skills/calebzu/pmsm-control-claude-skills-for-matlab/motor-smc-pmsm"><img src="https://agentmods.dev/badge/skills/calebzu/pmsm-control-claude-skills-for-matlab/motor-smc-pmsm/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/calebzu/pmsm-control-claude-skills-for-matlab/motor-smc-pmsm"><img src="https://agentmods.dev/badge/skills/calebzu/pmsm-control-claude-skills-for-matlab/motor-smc-pmsm.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 | $0.00257 | $0.02640 |
| Opus 5.5 | $0.00103 | $0.01056 |
| Sonnet 5.5 | $0.00051 | $0.00528 |
| Haiku 4.5 | $0.00026 | $0.00264 |
Grade A, and why
motor-smc-pmsm 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 2mo 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.
motor-smc-pmsm — PMSM Sliding Mode Control Speed-Loop Builder
Three-phase 2-level voltage-source inverter + PMSM. Outer-loop = PD-type sliding surface + Super-Twisting Algorithm (STA) providing iq_ref (continuous through s=0, second-order SMC). Inner-loop = dq current PI ×2 with cross-decoupling feedforward (PZC for RL plant + BEMF compensation). Modulation = Anti_Park + SVPWM library blocks. v1 baseline supports SPMSM and mild-saliency IPMSM (Lq/Ld < 2); strong-saliency IPMSM MTPA mid-loop deferred.
Layered on motor-pmsm-base. All base discipline applies.
⚠️ Signing Authority Note (SMC-specific)
Most users may lack independent SMC domain expertise. When the user declares this gap, switch to AI-self-audit mode (see base/theory_anchor.md):
- §A/§B (PI / DTC) formulas: user-signed
- §C (SMC) formulas: AI-self-audited with verifiable sources (≥ 2 independent cross-check + ≥ 1 link openable + ≥ 1 PDF cached)
Fail-safe replacement for user formula sign-off: a Phase 8 G4 user visual review on MATLAB desktop (4 Scopes + abc currents AC sinusoidal verification). G4 cannot be skipped.
Must-Follow Rules
- Plan first — Numbered plan with 25-input table, design-decision choices (design_decisions.md), build-script structure. Get user approval.
- One-click reproducibility — Inject all parameters via
set_param(mdl, 'InitFcn', ...). See crit_conditions.md §D-CRIT. - PD-type sliding + STA architecture —
s = e + λ·de/dt(Filtered Derivatives/(Tf·s+1)) + STA reaching lawu = K1·|s|^0.5·sgn(s) + K2·∫sgn(s). Do NOT use PI-type sliding (integrator wind-up voids Lyapunov proof) or classic sgn / boundary-layer sat (chattering). See control_law.md. - iq_ref Saturation is mandatory — Saturation block at
iq_refoutput BEFORE feeding to current PI, limits±iq_max. See crit_conditions.md §B-CRIT. - Lyapunov STA gains auto-computed;
B > 0in v1 baseline —K1 > 1.5·√M,K2 > 1.1·MwhereM = (TL_max + B·ω_max)/J. Build script asserts both. Plant frictionB > 0is the v1 baseline assumption (validated envelope; not a theoretical requirement — STA convergence is damping-independent). See control_law.md and crit_conditions.md §C-CRIT. Goto_The TagVisibility='global'MANDATORY — Anti_Park's internalFrom "The"requires the parent'sGoto_Theto publish globally; default'local'is silent failure mode (FOC degenerates to lab-frame open-loop). See base/broken_foc_diagnostics.md §F-CRIT 1 + crit_conditions.md §G-CRIT.- FF Mux input is
ω_e(NOTθ_e) — Cross-decoupling FF formulas need electrical angular velocity, not position. Use a dedicatedGain_Pn_omegablock independent ofGain_Pn(which provides θ_e forGoto_The). See ff_decoupling.md and crit_conditions.md §H-CRIT. - Add 4 Scopes for human inspection —
Scope_wm_RPM/Scope_iq/Scope_s/Scope_Te. See crit_conditions.md §F-CRIT. Visual 4-check (motor rotates / iq tracks / abc AC sinusoidal NOT DC-locked / Te energy balance) is mandatory pre-condition for trusting any numerical metric. - Solver =
ode3+ZeroCrossControl='DisableAll'— STA'sSignblock is discontinuous. Variable-step or ZC ON causes step explosion. See crit_conditions.md §E-CRIT. - SVPWM sector=7 startup workaround — At t=0 transient,
Vα=Vβ=0makes the SVPWM library'sSector_Caculateoutput sector=7 (invalid). Apply local-instance workaround on the library block. See svpwm_workaround.md.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 95 lines · 257 tokens per session scan A 55876d6616da
motor-smc-pmsm is a skill published in the GitHub repository calebzu/pmsm-control-claude-skills-for-matlab (15 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 257 tokens to every session and 2,640 once invoked, about $0.0010 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 2026-08-30.
motor-smc-pmsm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| motor-smc-pmsmcalebzu/pmsm-control-claude-skills-for-matlab | Skill | 15 | 4mo ago | Apache-2.0 | A | 257 | Claude Code |
| matlab-robotics-autonomywzyn20051216/matlab-agent-skills | Skill | 30 | 8d ago | MIT | A | 129 | Claude Code, Codex |
| matlab-simulate-radar-detectionsmatlab/matlab-agentic-toolkit | Skill | 1.3k | yesterday | none | A | 92 | Claude Code |
| matlab-design-dsphdl-ddcmatlab/matlab-agentic-toolkit | Skill | 1.3k | yesterday | none | A | 74 | Claude Code |
| matlab-transmit-capture-usrpmatlab/matlab-agentic-toolkit | Skill | 1.3k | yesterday | none | A | 145 | Claude Code |
| matlab-analyze-ams-waveformmatlab/matlab-agentic-toolkit | Skill | 1.3k | yesterday | none | A | 90 | Claude Code |
| matlab-analyze-emmatlab/matlab-agentic-toolkit | Skill | 1.3k | yesterday | none | A | 143 | Claude Code |