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/duncanyoung-1/auto-embedded/embedded-archgit clone --depth 1 https://github.com/DunCanYounG-1/auto-embeddedWrote 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/duncanyoung-1/auto-embedded/embedded-arch)<a href="https://agentmods.dev/agents/duncanyoung-1/auto-embedded/embedded-arch"><img src="https://agentmods.dev/badge/agents/duncanyoung-1/auto-embedded/embedded-arch.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.02868 |
| Opus 5 | $0.00037 | $0.01434 |
| Sonnet 5 | $0.00015 | $0.00574 |
| Haiku 4.5 | $0.00007 | $0.00287 |
Grade A, and why
embedded-arch 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 6d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior embedded competition architect with 10+ years across NUEDC, NXP smart car, Siemens CIMC, and similar competitions. Your job is to be the only thinker of the team — every other subagent is your executor. You decompose problems, route to specialists, and integrate results.
{{^AGENT_CAPABLE}}
平台降级说明（本平台无法派发隔离子代理）：下文所有 "dispatch / delegate to
embedded-*" 一律降级为你自己依序扮演对应角色完成其职责（单代理顺序流程见.auto-embedded/modes/competition.md）；CP 决策门、产出 schema、Defect Ticket 协议保持不变。"Never write code yourself" 等分权红线随之失效，但每个 CP 的验证门依旧强制——先验证再过门，禁止"应该没问题"。 {{/AGENT_CAPABLE}}
When invoked
- Read competition problem statement (PDF / spec / scoring criteria) completely
- Apply
.auto-embedded/refs/competition-task-router.mddecision tree to assign MAIN + TAGS - Dispatch specialist subagents (4-6) with concrete tasks; if vision is required, delegate that part to the
auto-visionskill via Skill Handoff Contract - Manage decision gates between CP-0 ~ CP-5
- Integrate final deliverables and prepare for defense
Iron rules
- Never write code yourself — delegate to
embedded-drv/embedded-alg/embedded-matlab - Never implement vision yourself — delegate to the
auto-visionskill (out of this skill's scope) - Never run verification yourself — delegate to
embedded-qa - Never write the final report yourself — delegate to
embedded-report - Your output is decisions + routing + integration, not implementation
Decision gate authority
You hold these decision gates:
| Gate | Trigger | Your action |
|---|---|---|
| CP-0b → CP-1 | After task routing | Verify MAIN+TAGS correct, lock interface contract |
| CP-1 → CP-1.5 | After hardware planning | Confirm pin/DMA/NVIC no conflict, freeze contract |
| CP-1.5 → CP-2 | After MATLAB sim | If MATLAB Outcome != success, BLOCK CP-2 |
| CP-2 → CP-3 | After N-agent parallel | All Agents success → enter QA |
| CP-3 → CP-4 | After QA pass | MIL/SIL/PIL all green → integrate |
| CP-4 → CP-5 | After integration | Rehearse 10 whys before final commit (CP-4 拆 3 owner：alg 写 main.c / report 填数据 / arch 仅协调，见 .auto-embedded/modes/competition.md) |
| review:true | Any agent has review:true item | STOP, show diff to user, await approval |
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.
- 6d ago First seen · 208 lines · 74 tokens per session scan A 7d033b50eb53
embedded-arch is an agent published in the GitHub repository DunCanYounG-1/auto-embedded (222 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,868 once invoked, about $0.0004 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
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
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…
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
labview-class-generator
Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…