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 commands/jannleo/telinksdk-builder-mcp/flashgit clone --depth 1 https://github.com/JannLeo/telinksdk-builder-mcpWrote 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/commands/jannleo/telinksdk-builder-mcp/flash)<a href="https://agentmods.dev/commands/jannleo/telinksdk-builder-mcp/flash"><img src="https://agentmods.dev/badge/commands/jannleo/telinksdk-builder-mcp/flash.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 | $0.00031 | $0.00986 |
| Opus 5 | $0.00015 | $0.00493 |
| Sonnet 5 | $0.00006 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
flash 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用通用构建运行器 ${COCO_PLUGIN_ROOT}/trae_build_runner.py 的 flash 子命令,对 ${workspaceFolder} 仓库进行烧录/读/复位(调用 Telink bdt.exe / Cmd_download_tool.exe)。
参数路由
根据 $ARGUMENTS 构造一条 python 命令并用 Bash 工具执行:
- 第一个参数视为 bdt 命令(
wf/rf/rst/ac/lf/wc/rc/wa/ra/wo/ro/pc/sws/help),用--command传递。 - 其余参数原样透传给 runner 的
flash子命令。
常用调用
# 烧录最新固件(自动取 build_variants 下最新 .bin)
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command wf
# 烧录并验证 + 失败重试 3 次 + 烧前预检(产线推荐组合)
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command wf --pre-check --verify --retry 3
# 指定芯片和输入文件烧录
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command wf --chip TC122X --input build_variants/app.bin --erase
# 多设备:用 SN 精确定位
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command wf --device-id 61174f1a603
# 读 flash 前 16 字节
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command rf --address 0 --size 16 --output read.bin
# 复位
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command rst
# 预览命令不执行
python "${COCO_PLUGIN_ROOT}/trae_build_runner.py" --project "${workspaceFolder}" flash --command wf --dry-run
选项速查
| 选项 | 说明 |
|---|---|
--chip |
bdt 芯片名(TL721X/B80/TC321X;空=builder.json flash.default_chip 或从预设推断) |
--command |
bdt 命令(默认 wf) |
--address |
地址,十进制(默认 0) |
--input |
-i 输入文件(wf 空=最新 .bin) |
--output |
-o 输出文件(rf/rc/ro) |
--size |
-s 大小(如 512k) |
--erase |
-e 写前擦除 |
--device-id |
BDT 设备 id:数字(1,2) 或 SN 十六进制串;空=配置默认(1) |
--verify |
wf 后读回前 64 字节与文件对比 |
--retry N |
wf 失败时重试 N 次,每次先跑恢复序列(ac→rst→ac→lf) |
--pre-check |
wf 前先 ac 探测芯片是否连接(仅 EVK 模式) |
--timeout |
覆盖超时秒数 |
--dry-run |
只打印 bdt 命令不执行 |
汇报规范
解析 runner 的 JSON 输出后向用户汇报:
- 成功:status、chip、device_id、耗时、attempts(重试次数);若有 verify,报告 verify_detail(match/mismatch)
- 失败:exit_code、error_reason(结构化诊断,如 "chip not found"、"address out of range")、attempts
- dry-run:展示完整 bdt 命令(含 cwd 提示:Cmd_download_tool.exe 需在自身目录执行)
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.
- 4d ago First seen · 66 lines · 31 tokens per session scan A 195ffe966061
flash is a command published in the GitHub repository JannLeo/telinksdk-builder-mcp (1 stars, last pushed 25d ago), licensed MIT. It adds 31 tokens to every session and 986 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
observe
部屋を能動的に観察する。3つの基本ブロックを自由に選びながらループし、受動的なスナップショットではなく発見のある観察を行う。.
model
Check if an AI model fits on your GPU before downloading.
tapeout
Produce a complete, fab-ready export bundle for a routed board — or refuse loudly. Superset of /kct:manufacturing-readiness: runs the three sign-off pre-gates, then adds a BOM part-number-resolution gate, a per-rule warning-review gate (assembly-affecting warnings block unless explicitly acknowledged), schematic +…
compliance-matrix
Gestiona matriz de conformidad con estándares regulatorios (CE, FCC, UL, RoHS, ISO). Permite definir estándares, trackear estado de requisitos, vincular evidencia, identificar gaps y generar reportes de cumplimiento.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
cisco-catalyst-ta-setup
Configure and validate the Cisco Catalyst Add-on (TAciscocatalyst), including SD-WAN API/BFD, UTD and ZBFW syslog routing, Cyber Vision, ISE, Catalyst Center, and the beta IOS-XE CLI collector.